Assignment 7 EMATM0061: Statistical Computing and Empirical Methods, TB1, 2024 Introduction This is the 7th assignment for Statistical Computing and Empirical Methods. This assignment is mainly based on Lectures 18, 19, and 20 (see the Blackboard). You can optionally submit this assignment by 13:00 Monday 11th November. This will help us understand your work but will not count towards your final grade. The submission point can be found under the assignment tab at Blackboards (click the title “Assignment 07” and upload a pdf file). Load packages Some of the questions in this assignment require the tidyverse package. If it hasn’t been installed on your computer, please use “install.packages()” to install them first. To load the tidyverse package: library(tidyverse) 1. One sample hypothesis testing 1.1 One sample t-test on penguins data In this question, we will apply one sample t-test to the population mean of the Adelie penguin’s bill lengths. (Q1) Begin by loading the “Palmer penguins” library. Next extract a vector called ““bill_adelie”” consisting of the bill lengths of the Adelie penguins belonging to the Adelie species. Carry out a statistical hypothesis test to test the hypothesis that the population mean of the Adelie penguin’s bill lengths is 40 mm. Use a significance level of 0.01. You can use the “t.test()” function. What assumptions are required for this hypothesis test? 1.2 Implementing a one-sample t-test (Q1) Implement a function that carries out a two-sided one-sample t-test. Your sample should take in two arguments 1) a vector “x” corresponding to a sample X1, ⋯ ,Xn ∈ N(μ, σ 2) and 2) the value μ0 corresponding to a null hypothesis of μ = μ0. The output of your function should be the corresponding p-value of the test. You can test your implementation by confirming your function gives the same p- value as the “t.test()” function for the example in question 1.1(Q1) of the assignment. 2. paired t-test and effect size The Barley data set gives the yields of two types of barley - Glabron and Velvet across twelve different fields. The data is paired as yields are given for both types of barley across each of the twelve fields. Install the package called “PairedData” first (if you haven’t done so) and then load the data: library(PairedData) # you might need to install the package first data("Barley") detach('package:PairedData', unload=TRUE) detach('package:MASS', unload=TRUE) # unload package because it contains another select() function head(Barley, 4) ## Farm Glabron Velvet ## 1 F01 49 42 ## 2 F02 47 47 ## 3 F03 39 38 ## 4 F04 37 32 (Q1) Carry out a paired t-test to determine whether there is a difference in average yield between the two types of barley. Use a significance level of 0.01. You can use the t.test() function. (Q2) Compute the effect size using Cohen’s d statistic. (Q3) What assumptions are required for the paired t-test? Are these assumptions justified in this case? 3. Implementing unpaired t-test In this question the goal is to create a function called “t_test_function()” which implements an unpaired Student’s t-test, in order to test for a difference of population means between two unpaired samples from two distributions. Your function will play a similar role to the following standard R function: t.test(body_mass_g~species, data=peng_AC,var.equal = TRUE) Begin by creating a data frame called ““peng_AC”” which is a subset of the Palmer penguins data set consisting of all those penguins which belong to either the ““Adelie”” or the ““Chinstrap”” species of penguins. library(palmerpenguins) peng_AC% drop_na(species,body_mass_g) %>% filter(species !="Gentoo") head(peng_AC %>% select(species, flipper_length_mm, body_mass_g), 5) ## # A tibble: 5 × 3 ## species flipper_length_mm body_mass_g ## ## 1 Adelie 181 3750 ## 2 Adelie 186 3800 ## 3 Adelie 195 3250 ## 4 Adelie 193 3450 ## 5 Adelie 190 3650 (Q1) First, try to understand what the following piece of code does. val_col % summarise(mn=mean(val)) data_new ## # A tibble: 2 × 2 ## group mn ## ## 1 Adelie 3701. ## 2 Chinstrap 3733. data_new$mn[2] ## [1] 3733.088 Now, let’s create the function “t_test_function()” . Your function should take in the following arguments: 1. ““data”” - A data frame. argument, 2. ““val_col”” - A string argument. This argument is for the column name for a continuous variable (e.g., the body mass column “body_mass_g”), 3. ““group_col”” - A string argument. This argument is for the column name for a binary variable (e.g., the species column “species”). The function should carry out an unpaired Student’s t test based on the value of the continuous variable in the column whose name is stored in “val_col”: 1. The function should begin by partitioning the sample into two groups based on the value of the binary variable named ““group_col”” . For example, suppose that the column ““group_col”” contains entries “Adelie” and “Chinstrap”, then you should partition the sample into two groups corresponding to “Adelie” and “Chinstrap” respectively. You can use the “group_by()” function. 2. Your function should then compute the sample mean, sample variance and sample size for each of these two groups, based upon the variable within the column whose name is stored in ““val_col”” . 3. Your function should compute a test statistic for the Student’s unpaired t-test (Lecture 20). In addition, the function should compute the corresponding p- value. Finally, your function should compute an estimate for the effect size. 4. Your function should return a data frame containing the test statistic, p-value and effect size. Your function should have the following output: t_test_function(data=peng_AC,val_col="body_mass_g",group_col="species") ## t_stat effect_size p_val ## 1 -0.5080869 -0.07420226 0.6119085 (Q2) As an additional challenge you can modify your function so that it takes a fourth argument called ““var_equal”” which takes a Boolean value. If the input of ““var_equal”” is the Boolean “TRUE” your function should compute the test statistic and p-value for an unpaired Student’s t-test. If, on the other hand, the input of ““var_equal”” is the Boolean “FALSE” your function should compute the test statistic and p-value for Welch’s t-test. Your function should have the following output: t_test_function(data=peng_AC,val_col="body_mass_g",group_col="species", val_equal=FALSE) You can compare the output of your function with R’s inbuilt “t.test()” function. 4. Useful concepts in statistical hypothesis testing This question is about the basic concepts in statistical hypothesis testing. (Q1) Explain the following concepts. The aim is to get familiar with these definitions. Try to do this yourselves but you may want to go back to the lectures 18 and 19 to find the definitions if needed. 1. Null hypothesis 2. Alternative hypothesis 3. Test statistic 4. Type 1 error 5. Type 2 error 6. The size of a test 7. The power of a test 8. The significance level 9. The p-value 10. Effect size (Q2) (1). Is the p-value the probability that the null hypothesis is true? (2). If I conduct a statistical hypothesis test, and my p-value exceeds the significance level, do I have good evidence that the null hypothesis is true? 5. Investigating test size for an unpaired Student’s t-test In this question, we shall investigate the performance of an unpaired Student’s t-test from the perspective of test size. Recall a Type 1 error occurs when we reject the null hypothesis when the null hypothesis is true. The size of a test is the probability of a Type 1 error. A key property of valid statistical hypothesis tests with a given significance level is that the size of the test does not exceed the significance level. Note that we can apply unpaired Student’s t-test with significance level alpha on a samples “sample_0”, “sample_1”: t.test(sample_0,sample_1,var.equal = TRUE, conf.level = 1-alpha) We can apply an unpaired Student’s t-test and extract the p-value as follows: t.test(sample_0,sample_1,var.equal = TRUE)$p.value Notice that the significance level wasn’t supplied as an argument. Is this a problem? The following code checks the size of an unpaired Student’s t-test with a significance level of α = 0.05. num_trials
EES1132/EESD21 Final Project Deadlines: October 29 and November 26 and December 10, 2024 Introduction The primary goal of this project is to allow you to independently apply your new data analysis skills to a climate change or geophysics problem of your choice. You are expected to use several of the methods learned in class to ask and answer a research question using climate or other geophysical data and to tell a coherent and interesting story. Project Components (Total Marks: 100) 1. Project Proposal + Goal-Setting (Oct. 29, 2024) 10 marks 2. Class Presentation with peer-feedback (Nov. 26, 2024) 10 marks 3. Project Report (Dec. 10, 2024) 80 marks 1. Project Proposal + Goal-Setting The first phase of the project is to choose a topic, find the data and write up a project proposal. Your proposal along with a your project goals and timeline (~4-5 pages, double-spaced) are due October 26, 2024. Please discuss your topic with Prof. Mirza before the deadline. One of the key evaluation criteria of the project proposal is feasibility. This means that you must find the data you require to complete your project as part of your proposal. Don’t delay trying to find your data! A rubric for the proposal is included in a separate document. Submit your proposal via Quercus by 23:59 ET on October 29st, 2024. 2. In Class Presentations During the final class, November 26, 2024, we will hold an in-person presentation session. During the presentation session (5 Minutes), we will all get a chance to view and give feedback on each other’s work. Specifically, you will create a presentation that describes your research question (s), identify the data you are using, present preliminary analysis including at least one figure, and outline the next steps you will take to complete your project. You will be required to complete a peer evaluation form for each presentation you view as part of your class participation grade. A rubric for the presentation is included in a separate document. Submit your recorded presentation via Quercus by 11:59 ET on November 26th, 2024. 3. Project Report Write up your analysis in the style of a scientific journal article (Abstract, Introduction, Methods, Results, Conclusions), maximum of 20-pages (double-spaced), 5 figures and 2 tables. Note that one figure can have multiple panels. A journal article of this length is what is known as a letter. Look at the journal Geophysical Research Letters, for some examples. The deadline for the final report is December 10, 2024. A rubric for the report is included in a separate document. Submit your report via Quercus by 23:59 ET on December 10th, 2024. Final Note A successful project does not necessarily mean that you find a novel, robust statistical result that supports your hypothesis - your analysis might not support your hypothesis at all and that’sok. A successful project is one that clearly states a plausible research question and hypothesis, addresses the question/hypothesis using the most relevant data and most appropriate statistical methods (within the scope of this course) and thoughtfully interprets the results, e.g. discussing underlying assumptions, confounding variables, data quality/quantity, etc.
Server Side Systems CW02 Academic Year: 2024-2025 Term: 1 TECHNICAL ASPECTS OF LARAVEL BASED ON THE DEMO PRESENTATION (UP TO 30 MARKS) Marks will be awarded based on the technical skills demonstrated during the demonstration of your Laravel application, accounting for 30% of the entire Honours module. Key Areas for Assessment: • Basic Implementation: Some students may choose to enhance an existing application (e.g., a lab exercise). Note, however, that no credit will be given for unchanged database designs. • Core Functionality: User authentication and authorisation are essential for any real-world application. Incorporating file uploads and serving files will also be important aspects. • Use of Taught Techniques: Students who primarily use the techniques taught in lectures and labs will demonstrate solid foundational skills. By referencing class materials during your presentation (e.g., “as discussed in Week X, Slide X”), you not only show your engagement with the module but also provide clear evidence of how you have applied course content to your project. Higher Marks Criteria: To achieve higher marks, students are encouraged to go beyond the basics and demonstrate more advanced skills. This may include: • Developing from Scratch: Building a Laravel application entirely from scratch, rather than adapting a lab exercise. • Using Advanced Techniques: Incorporating specialised Laravel techniques not covered in lectures or labs, showcasing independent learning and technical exploration. • Fully Debugged Work: Presenting a thoroughly tested and debugged application. • Enhanced Functionality: Implementing features such as user roles, user management, backend administration, or superuser capabilities, all of which demonstrate a deeper understanding of Laravel. Demonstrate the following: 1 Basic CRUD Functionality: Show that your application can perform. basic Create, Read, Update, and Delete (CRUD) operations, essential for most web applications. 2 Models: Present your database design and demonstrate the use of validation rules within your models, ensuring data is correctly managed and validated. Discuss your Eloquent ORM (Object Relational Mapping) implementation. 3 Database Migrations: Showcase the migration files you created for this academic year. Clearly explain how these migrations were generated, how they work, and how they integrate with your current database structure. 3 User Accounts, Authentication, and Authorisation: Demonstrate how your application handles user registration, login, and roles/permissions. 4 Specialised Techniques: Highlight any advanced or unique Laravel techniques you’ve used in your project, beyond what was covered in the course. 5 User Interface Improvements: Show the UI/UX enhancements you’ve implemented, such as responsive design, navigation improvements, or user-friendly features. Present the overall visual design of your site, including layout, styling, and use of CSS to enhance the user experience. 6 Deployment: Demonstrate that your application is deployed on a publicly accessible domain with HTTPS security, hosted on the AWS platform. CONTENT OF THE WRITTEN LARAVEL PROGRESS REPORT (UP TO 30 MARKS) The written progress report should focus exclusively on your Laravel development work. It is a formal and substantial piece of work, accounting for 30% of the entire Honours module. The report must not be a general review of Laravel, but rather a detailed record of your personal development journey with the project. Key Areas for Assessment: Your Laravel progress report should clearly demonstrate essential graduate-level skills by documenting your ability to: • Analyse Problems: Identify and explain the challenges you encountered during your development. • Introduction and Conclusion: Don’t forget to provide a structured introduction to your project and a well-rounded conclusion summarising your progress and findings. • Synthesise Solutions: Provide solutions to the problems you faced, showcasing your ability to apply critical thinking and technical knowledge. • Code Samples: Include relevant code samples, thoroughly explained and discussed, to communicate your understanding of Laravel and the technical decisions you made. • Apply Course Material: Show how you applied the techniques and concepts taught in lectures and labs to your project. Referencing Slides or specific labs of this module (e.g., “as discussed in Week X, Slide X”), you not only show your engagement with the module but also provide clear evidence of how you have applied course content to your project. • Communicate Understanding: Ensure that your explanations are clear, focused, and demonstrate a deep understanding of the technical aspects of Laravel. Higher Marks Criteria: To achieve higher marks, your progress report should include: • Detailed Analysis of Challenges: Address significant issues you faced with your development environment, toolchain installations, or web server configuration, and how you solved them. These challenges provide an opportunity to showcase your problem-solving abilities. • Develop Skills Beyond the Classroom: Demonstrate how you went beyond the material provided in the course, applying new or advanced Laravel techniques. Everything must be properly referenced using UWS Harvard style. • Learn Lessons and Make Recommendations: Reflect on the lessons learned throughout the project, draw conclusions, and make recommendations for future work or improvements. +Include & discuss appropriate code samples to communicate understanding!!! Provide the following: 1 Organisation, Structure, and Presentation: The report should be well-organised, with a clear structure and professional presentation. Ensure that your content is easy to follow, with logical flow between sections. Include relevant comments and observations to enhance clarity. 2 Project Overview: Clearly describe the nature and goals of the Laravel application you developed. This should include the purpose of the project and any specific features or functionality that were implemented. 3 Practical Progress and Challenges: Provide a detailed account of your development progress, outlining any difficulties you encountered and the solutions you implemented to overcome them. Show how you approached problem-solving throughout the project. 4 Code Extracts and Documentation: Include relevant code extracts that showcase the use of Laravel techniques in your project. These extracts should demonstrate advanced usage of Laravel, highlighting your technical skills. 5 Explanation and Understanding of Code: Ensure that your code extracts are accompanied by clear explanations. These explanations should reflect a deep understanding of relevant concepts such as web development, HTTP protocols, security, PHP, MVC architecture, Laravel, RDBMS (Relational Database Management Systems), etc. 6 Project Deployment and Accessibility: Provide details of how the project was deployed and made accessible. Include the steps taken to host the application on a public server, any security measures (e.g., HTTPS, authentication), and ensure the application is accessible for review and assessment. Provide GitHub access to your project for code review. 7 Lessons Learned and Conclusions: Summarise the key lessons you learned during the project. Your report should also include conclusions or recommendations based on these lessons, discussing how your experiences might inform. future development work. ASSESSMENT CRITERIA AND GUIDELINES All the sections above will be assessed using the following criteria. To achieve a good mark, ensure that your report demonstrates essential Honours graduate-level skills. Specifically, your work should: • Analyse problems effectively. • Synthesise solutions based on your findings. • Clearly explain the steps you took in your own words. AI-generated text for concepts and theory will not be assessed. • Reflect on the lessons you’ve learned throughout the process. • Draw logical conclusions from your work. • Make recommendations where appropriate. • Select the most relevant images to illustrate your understanding of the diagnosis and debugging techniques, showing that you grasp the significance of the information presented in each image. • Communicate your understanding, rather than simply copying sections from a manual or AI generated texts. • Choose text extracts that highlight the most important and relevant features, demonstrating your insight into the process. Select file extracts that are most appropriate. • Ensure your documentation is related to your specific project, as this demonstrates that your report is based on your own work, making it harder to falsify. • Make sure any images included are of individual windows (rather than full-screen captures), so they remain clear and legible when scaled to fit into an A4 PDF document (e.g., font size 10-12, at 100% zoom in a PDF viewer). • Use captions and figure numbers for all images and refer to them clearly within the supporting text. This will ensure your explanations are well-supported and easy to follow.
Syllabus STRATEGY PGE M1 Fall, 2024 STRATEGY Academic year 2024-2025 COURSE DESCRIPTION Formulating a sound competitive strategy and achieving growth across multiple, different business units to sustain long-term superior performance are two of the critical tasks for general managers to ensure the success of the firms they lead. The objective of this course is to provide students with an opportunity to understand, through analytical approaches and critical thinking, how companies make strategic decisions to support the development of competitive advantages, corporate growth and shareholder value through the simultaneous pursuit of economic as well as social and ecological performance dimensions. We will focus on strategic issues from the viewpoint of senior management in both domestic and international corporations. Through a combination of lectures, readings, case studies, experiential exercises and a consultancy project, this course introduces students to the tools and knowledge required for critical and effective strategic analysis, thinking, and application. Mastery of these tools and knowledge has relevance to everyone seeking a career in strategy as a manager, an entrepreneur, or a consultant. The course will help students develop a general management point of view and appreciate strategy to the firm's overall growth and welfare. You will learn how to analyze the firm, and its environment, and then align strategies to the firm’s revenue and profitability goals. You will work in teams on selected companies to produce a final consultancy project. This course will require hard work and thinking, augmented by your creativity, to produce a fun and enriching experience. COURSE OBJECTIVES 1) Demonstrate working knowledge of fundamental concepts in strategic management; strategy identification and evaluation; industry analysis; competitive challenges; and company and industry evolution. 2) Understand the impact of environmental forces and of strategic actions by the firm and its rivals on business and corporate strategy. 3) Develop data literacy skills and competencies in assessing and selecting appropriate data sources for strategic analysis. Demonstrate and apply analytical and critical thinking in reporting analysis, inferring conclusions effectively, and framing practical recommendations. 4) Develop skills in logical strategic thinking, responding to comments, and justifying your position in discussions with quantitative data and evidence. LEARNING ENVIRONMENT A willingness to attend, prepare classes in advance, and participate actively is the central ingredient for succeeding in this course. A few essential points concerning our classes: a. You must prepare each class (both lectures and tutorials) in advance. We plan to be prepared for every class and we expect you to do the same. Before each class (both lecture and tutorial formats), get informed on what you are supposed to do. Your diligent work prior to class is essential for achieving our learning objectives. b. Attendance is mandatory. If you must miss a class, we expect you to notify your instructor by email in advance. c. Classes start on time. We do arrive punctually to class, and we expect you to do the same. d. Electronic devices. Use of electronic devices in class is not allowed except in answering poll questions during class and taking notes. e. Regularly check your SKEMA emailbox for communications and updates. f. You must form. and organize your team for TD sessions. You are responsible for forming your own teams by a pre-assigned deadline. Otherwise, you will be randomly assigned to a team by the instructor before the first tutorial session. The teams’ composition cannot be changed. g. Free riding will be sanctioned. We expect you to remain engaged and contribute to the team assignments throughout the course. Your instructor reserves the right to apply grade penalties to sanction free riding. PEDAGOGICAL APPROACH We will use a combination of (a) theory and (b) a team project. a. Lectures (CMs) will introduce theoretical and conceptual frameworks for strategic management and showcase different real-world applications, which will help analyze strategic problems and develop solutions to deal with these situations. • Theory-focused sessions are designed to present and explain relevant theoretical frameworks. • Case-focused sessions show application cases on different industry and company situations and support your learning and understanding with a strategy conversation of the week, i.e., a debate on the case of an industry or the strategy of a company. b. Tutorials (TDs) are meant to help you become familiar with the role of strategic analysts and consultants. The project will simulate a consultancy assignment. In teams of maximum five members, you will work on a company at your choice among a pre-selected set, collect, and quantitatively analyze information about the company’s strategy from available sources, and prepare and verbally present two PowerPoint consultancy presentations (mid-term and final) based on the results of your analyses, covering the following aspects: (a) the company’s external environment (i.e., industry analysis) (mid-term), (b) its business strategy (mid-term), (c) its resources and capabilities (mid-term); and (d) the company’s corporate strategy (final); and (e) final evidence-based recommendations (final). The presentations will be worked will be worked and verbally presented during the tutorial sessions (refer to the outline below). Details about the deadlines will be announced during the course on the K2 platform. COURSE MATERIAL Textbook Rothaermel FT. 2024. Strategic Management, 6th Edition. McGraw-Hill. The SmartBook is available on the McGraw-Hill CONNECT learning platform at the link provided. Course Pack, Lecture Slides, Case Studies, and Assignments The course pack (including guidelines for the consultancy presentations), lecture slides, case study materials (including case description, data, appendices, and questions for preparing the in- class discussion) will be posted on the course page on K2. Video Tutorials on Strategic Analysis in Excel Pre-recorded tutorials on how to execute the strategic analyses to be included in the consultancy assignment will be made available on the K2 platform. Additional Recommended Resources You are expected to follow business news from a US newspaper or Journal (e.g., Wall Street Journal). Additional information from newspapers, journals and ‘think tanks’ (e.g, McKinsey, Deloitte, Gartner, etc.) are recommended to enhance the value you will receive from this course. These maybe available online or through SkemaLearn. Software and Systems This class will make use of Microsoft tools (Word, PowerPoint, Excel.) In addition, it maybe useful to use document sharing software for your teamwork for version consistency.
CHEM 140 - Sample Final Evaluation Please read the following instructions carefully. You may use either Excel OR Mathcad to answer the following problem. NOT BOTH! Not all required items are specified in the in the instructions. You must decide what is important and should be included in the solution of this problem. For example, items such as standard deviations, error bars, correlation coefficients, etc, must be included where appropriate and/or necessary. You may be required to refer to the CHEM 140 manual for some pertinent equations/formulas. The method of standard addition is used in instrumental analysis to determine the concentration of a substance (analyte) in an unknown sample. In this method, a known amount of the analyte is added to the unknown solution. A measured response of this solution is determined before and after the addition of the standard. From the measured response increase due to the increased analyte concentration, the original concentration can be determined. Since the measured response (signal) is proportional to analyte concentration, we can say that concentration of analyte in unknown signal from unknown concentration of analyte + standard in mixture signal from mixture The standard addition equation is given by Equation 1, where [X]i is the unknown initial concentration of the analyte, which yields a signal of IX. After the standard was added, [X]f is the final concentration of the unknown analyte and [S]f is the final concentration of the standard. After the standard was added, IX+S is the signal measured. If we define the initial volume of the unknown as V0, the volume of the standard added as VS, and final volume of the mixture as V (Note, V does not necessarily equal V0 + VS),the final concentrations of the unknown analyte and standard are given by Equations 2 and 3, respectively. By substituting the expressions for [X]i (Equation 2) and [S]i (Equation 3) into the standard addition equation (Equation 1) and rearranging, we obtain the expression given by Equation 4. An experimental analysis was conducted to determine theiron (Fe) content in drinking water. The drinking water was analyzed using the standard addition method, described above. The concentration of theiron (Fe) standard solution was 11.1 ppm. All solutions were diluted to a final volume of 50.0 mL. The iron in the drinking water samples were experimentally analyzed by using an instrument called an atomic absorption spectrophotometer (AAS). The experiment results are given in Table 1, below. Table 1 Sample Volume (mL) Standard Volume (mL) Signal 1 10.0 0.0 0.215 2 10.0 5.0 0.424 3 10.0 10.0 0.685 4 10.0 15.0 0.826 5 10.0 20.0 0.967 Using the given experimental data, determine theiron (Fe) concentration in the drinking water sample.
BUS001 Coursework Assignment: 80% Individual Essay Due date: TBD Submission: QMPLUS Turnitin Please follow submission instructions and guidelines Word Count: 1500-up to 2000 words (references excluded) QMUL SBM policy allows for students to submit a word count 5% above the word count or 5% below the required word count. Be mindful that exceeding well beyond the word count does not equal to better work! It is good academic discipline to stay within the required word count. References: As an academic assessment, you are required to use appropriate resources. You must include academic resources, which also entail module readings. You may also provide supporting evidence from reputable reports (e.g., Government websites, Case studies, News Reports, i.e., The Guardian). Websites like mindtools.com, Wikipedia, etc., will not be acceptable sources for this assignment. Please use Harvard Referencing Style. AI-Assistance: You may use AI to draft text and refine your work, i.e., proofreading, grammar, etc. Your final submission should show how you have developed and refined these ideas. You must critically evaluate and modify any AI-generated content you use. Tips: You are expected to submit individual independent work. Please construct an academic essay using appropriate language, style, structure, and referencing. *Essay Task: Consider the key components of Business Environment analysis (as discussed in the module) and the effect of globalization on an organization’s strategy. Describe and discuss how external environmental factors influence the internal business environment. Explain your answer using two or more PESTLE factors from the PESTLE framework. Reflect on globalization's benefits and challenges and identify at least one challenge or benefit to the internal business environment. Marked assignments exhibit the following features 80-100 High 1st 70-79.9 1st 60-69.9 2:1 50-59.9 2:2 45-49.9 3rd 40-44.9 Lower 3rd, pass 0-39 Fail Quality of information & Conclusions Argument structure very clear and strong, high level of rigour in inference. Focused exclusively on explanation / evaluation Argument structure very clear and strong. Focused exclusively on explanation / evaluation Argument structure clear and strong Principally explanatory / evaluative Argument structure either clear or strong but not both Largely descriptive Argument structure lacking in clarity and / or strength Mainly descriptive Argument poorly structured. Purely descriptive No clear argument Purely descriptive, perhaps vague even in description Critical Thinking Exceptional analysis, synthesis and critique Excellent analysis, synthesis and critique Very good analysis, synthesis and critique Good analysis, synthesis and critique Weak analysis, synthesis and critique Poor analysis, synthesis and critique Very poor analysis, synthesis and critique Structure Very strongly, clearly logically structured, headings grounded in clear principles of inference from evidence to conclusion Strongly, clearly logically structured, headings grounded in clear principles of inference from evidence to conclusion Competently structured, headings grounded in some principles of inference from evidence to conclusion Adequately structured, with headings bearing some relationship with logic of argument Weaknesses in structuring and/or in subheadings Serious weaknesses in organisation and structure of the essay No clear organisation or structure to the essay Referencing Broad number of sources drawn from. Good use of in-text citations and referencing listed in Harvard style Broad number of sources drawn from. Good use of in-text citations and referencing listed in Harvard style Good number of sources drawn from and referenced. Good number of sources drawn from and referenced. Some citations but inadequate referencing Few sources drawn from but not properly cited Poor sources/ no referencing
Advanced Excel: Excel Fundamentals review Module 1 Lecture Module 1 – Excel interface and basic calculations Outline Part 1 Excel interface and formatting • Visiting the Excel Interface - Overview of the Excel interface - Navigating ribbons and panels - Formula bar, Name Box, and Formula editor - Insert function and Editing area - Status bar and Zoom - Automatic calculator for selected area • Structure of the Excel Document - Renaming and organizing worksheets - Maximum number of columns and rows - Cell content types and limitations - Creating, saving, and opening workbooks - Deleting and reorganizing worksheets • Navigating the Workbook and Selecting - Keyboard shortcuts for navigation - Selecting regions and specific cells - Formatting and deleting cells - (optional) Accessing ribbon options with the keyboard • Managing Columns and Rows - Clearing contents and formats - Inserting and deleting columns and rows - Hiding and unhiding columns and rows - Resizing columns and rows • Formatting Cells - Changing display formats - Aligning text and adding borders - Merging cells and wrapping text • Building Charts - Creating and customizing charts - Moving charts to new worksheets - Customizing chart elements - Adding and formatting data labels Part 2 Formulas and Basic Calculations • Creating Formulas to Perform. Calculations - Typing formulas and using operators - Using cell references - Copying and reusing formulas - Absolute vs. relative cell references - Linking cells between worksheets and workbooks • Naming Cells and Ranges - Using predefined functions for calculations - Naming and using named ranges in formulas Part 3 Formulas with Basic function and Text Functions • Basics of Predefined Functions - Sum, Average, Product, Min, Max - Text functions (Len, Find, Trim, etc.) - Rounding functions (Round, Int, Trunc) - Counting functions (Count, CountA, CountBlank) Part 3 Formulas with Basic Date and Time Functions • Date and Time in Excel - Storing and using date and time information - Date and time functions Part 1. Excel Interface Visiting the Excel interface o Caption bar: AutoSave option (Office 365) o Ribbons navigate to different panels File button: File > Options > Customize Ribbon Formulas o Row: 1:1048576; Columns:A: XFD o Name Box: shows the coordinate of the cell/ find a far cell, e.g., Z3000/rename a cell, 20:00 o Insert function button: function library (>3000 functions in Excel) o Formula bar: display the formula used in a cell o Worksheet Tab o Zoom in/ out o Status Bar: Automatic calculator for the selected area, customize the results shown File: Module1 - Part1 Excel interface and formatting.xlsx Task 1: Create a new workbook o Method 1: File > New > Select a Blank workbook or from existing templates Task 2: Save a workbook o AutoSave: may not always be activated, depending on where you save it. Note: it will also overwrite the previous document. o File > Save (using the default name and format) o File > Save As > Customize the name/ format/ location. Task 3: Open an existing document o File > Open from OneDrive (saved in the cloud) o File > Browse, to select a local file Structure of the Excel document An excel file is a Collection of Worksheets in the opened Workbook Note: the number of worksheets is limited by the computers memory the worksheets default name depends on the language youre using in your Excel Task 4: Rename worksheet o right-click then select rename, or double-click Note: - The worksheet name cannot be empty, better to have a meaningful name, but not too long ( right-click > Delete o Select the region > Ribbon Editing > Clear Note: Right-click will give you different options depending on your selected object. • Access to the ribbon with the keyboard: Press Alt button o Alt H E C Managing Columns and rows • Insert columns: o Insert a new column (multiple columns) to the left: Select the column> Right-click the column label > Insert • Hide columns: Select the column > Right-click >Hide • Unhide columns: o Select the columns before and after the hidden ones > Right-click > Unhide • Hide and unhide rows • Re-size columns: o Manually adjust: put the mouse at the edge of the column, when it shifts to a vertical line with two arrows (flying mouse) directing both directions, right-click and drag o With given measurement: select the column/columns > right-click > Column Width > insert the pre-defined measurement o Autofit depending on the content: put the mouse at the edge of the column, when it shifts to a flying mouse > Double-click o Autofit multiple columns simultaneously: select columns > double-click any edge of the selected columns • Re-size rows: work the same as above Note: A hashtag sign # appears when the column width is too narrow to display the value Formatting the cells The cell contains two types of information: the value or function, and the display format. • Change display format o Ribbon Home o Select the region > Right-click > Format Cells Note: it does not mean the value has been changed. (Check the Formula Bar.) • Alignment • Font • Border Note: that even in the worksheet display, the gray grid is visible, however it will not be printed. We need here to add borders to the printed table. (Try File Print, see default result) • Wrap Text • Merge Cells and center Task 1: Display numbers with no decimal o Right-click > Format Cells > Number > Number > change Decimal places to 0. Task 2: Change selected column values to be in font Times New Roman, Angle 45 degrees clockwise, center horizontally and vertically, and display 2 decimals Task 3: Format the title, centered, bold, colored Building charts • How can I create a chart? o Select data > Ribbon insert > select a chart. The colored area shows the plotted data; Move and resize the chart Note: Click on the chart, Extra Dynamic Ribbons appear: Chart Design and Format • How to create a new worksheet with only the chart? o Click on the chart > Ribbon Chart Design > Move Chart > New sheet. • How to replace x-axis labels with values in another column? o E.g., replace labels 1, 2, … , as the students names o Click on the chart > Ribbon Chart Design > Select Data > Select Data Source, ( Legend Entries panel shows what info are contained in the plot, Horizontal (Category) Axis Labels shows the X-axis Label info) > Select Edit under Horizontal (Category) Axis Labels > select the students name values. o Warning! if you accidentally select an additional cell, a warning message will pop-up for the above option! – Check the selected area • How to customize the title? o Click and change • How to change the color of the bars? o Double-click one of the bars> In Format Data Series > Fill and Line > Series o Highlight only one bar: select the bar and change its color • How to change the scale in they-axis? o Double-click the virtual label > change Bounds and units • Transfer from a vertical bar chart to a horizontal bar chart. o Click on the chart > Ribbon Chart Design > Change Chart Type > Bar > vertical bar chart. • How to add data labels for each bar? o Ribbon Chart Design > Add Chart Element > Data Labels o Double click the Data Labels, you can customize it on the Format Data Labels • How to change the chart background? o Double click the background, select a picture on the right panel Format Chart Area Part 2 - Formulas with Basic Calculations Creating formulas to perform. calculations File: Module1 – Part 2 Using formulas.xlsx Worksheet: Typing a formula • Insert a formula: With =, e.g., = 3+4 • Show formulas: Ribbon Formulas > Formula Auditing > Show formulas Worksheet: Doing math with cells • The basic operations: +, -, *, /, ^, Note: o #DIV/0 means that the formula is trying to divide something by 0. o 3.5E+20 means 3.5 * 10^20 Worksheet: Comparing cells Boolean values: TRUE or FALSE Note: o true, True, tRue, … all recognized as TRUE o Do not insert a space between < and = for Calculation >Calculation Options, select Manual. o Click Run calculation to update the values. Worksheet: Reusing formulas Task 1: Calculate Average o L2: =(D2+E2+F2+G2)/4 r =AVERAGE(D2:G2) o Method 1: click I2, copy then paste in I3 o Method 2: put the mouse at the bottom right corner, when the mouse becomes copy handle (also called fill down), propagate to the end/double click. Task 2: Adjust for absence (each absence costs 2% of the avg) o J2: =I2-H2*2%*I2 Task 3: Check if the adjusted average is below or above the average of the class o Calculate the class average at J27: =AVERAGE(J2:J25) Note: To autofill the entire table requires absolute reference of cell J27: o K2: =J2=$J$27 Note: o Absolute reference: Lock row or column, put $ correspondingly o Shortcut: F4 Task 4: Check if the student succeeds with the result of the column "Above or equal to average" o M2 : "=L2" Naming range and cells Worksheet: Naming range and cells Ribbon Formulas, Function Library panel contains tons of built-in functions Task 1: Calculate the Min/Max/Average o K2: =MIN(G2:G25) o K3: =MAX(G2:G25) o K4: =AVERAGE(G2:G25) Task 2: Name region G2:G25 as FinalMark: o Select region G2:G25, and rename by typing FinalMark in the Name Box o Re-do the average calculation using the named region K4: =AVERAGE(FinalMark) Note: the FinalMark is an absolute reference, meaning $$. When you autofill move down the Average, the called region stays the same as FinalMark – different if you use =AVERAGE(G2:G25). Task 3: Rename the region D2:D25 as Mid1Marks, E2:E25 as Mid2Marks, F2:F25 as LabsMarks Task 4: Check existing named regions: Ribbon Fomulas > Defined Names > Name Manager. Worksheet: Using cells from dif. Sheets B2: ='Doing math with cells'!B2*'Comparing cells'!B2 Part 3 – Formulas with Basic and Text Functions Basic predefined functions Files:Module1 – Part 3 Basic and Text Functions.xlsx Function: = Function(Parameter 1, Parameter 2, … , Parameter n) result Note: Not recommend to type =SUM(B12+B13+B14…+B18), still works but it means the first Parameter is a sum of all cells. When you add another row in between 2 and 3, =SUM(B12+B13+B14…+B18) will not use the added new row. The SUM here is necessary. Use =SUM(B12:B18). When you add another row in between 2 and 3, =SUM(B12:B18) will use the added new row. A function will normally return one single output, but some of them may return a table of information. =ROUND(B12:B18, 0) will return all values rounded to the nearest integer Task 1: The sum of Table 1: o Method 1: Use the SUM function to add all the cells from a range, separate by comma ,. =SUM(C3,C4,C5,C6,C7,C8,C9,C10) o Method 2: Select the region using the mouse/keyboard (Shift). =SUM(C3:C10) Note: The difference between Method 1 and 2: if you add a new entity in row 5, the result by Method 1 will not include the new entity. Task 2: The sum of two regions, C3:C10 and F3:F10 o Type =SUM( Select the first region press Ctrl while selecting the other region Press Enter to see the result Note: if the two regions overlap, the values in the intersection region will be used twice. • Average C3,F3: =AVERAGE(C3,F3) • Average C3:C9:=AVERAGE(C3:C9) • Average C3:C9,F3:F9: =AVERAGE(C3:C9,F3:F9) Note: Use Ctrl to select an additional region • Min C3:C9: =MIN(C3:C9) • Max C3 :C9 : =MAX(C3:C9) Task: Calculate the length of all names using function LEN() LEN(text) reports how many characters are in this text o B3: =LEN(B3) in B3, then autofill Note: The space will be counted! E.g., B5 Pe ter has 6 characters. Task: Search within a text whether another text is present FIND(find text, within text, [start_num]) check if a subtext is within a specific text o [start_num]: at which position I am going to start search o [] means optional parameter Task: Extract 3 characters from a text, starting from position 4 =MID(Text from where to extract, beginning position, nr of characters) Trimming: remove spaces at the beginning and at the end, as well as the duplicated spaces in the middle Task: Trim text in C2 and check the trimmed and untrimmed text length Worksheets: Left and Right =LEFT(Text, number of characters): extract a certain number of characters starting from the beginning =RIGHT(Text, number of characters): extract a certain number of characters starting from the end Task: Concatenate text 1 (C2) and text 2 (C4) o Method 1 &: =C2&", "&C4 o Method 2 =CONCATENATE() : =CONCATENATE(C2,", ", C4) Task: concatenate text in a range o =CONCAT(C11:C15) Task: concatenate text in a range with common separator symbol and ignoring blank cell o =TEXTJOIN(", ";TRUE;C11:C15) Worksheets: Upper, Lower and Proper Change text into upper, lower and proper case =UPPER(text), =LOWER(text), =PROPER(text) Task: Get the integer part of a floating number o =Int(number): to get the integer part of a floating point number o Int(2.5) 2; Int(-2.5) -3 The resulting integer is always lower than the query value Task: Round a floating number =Round(number, number of decimal places): will round the number to a specific number of decimal places Task: Truncating a number to a specific decimal places =TRUNC(number, number of decimal places): truncates a number to a specific number of decimal places Note: it is different from rounding, as it only cuts the floating number up to the desired decimal place Task 1: Count the number of marks in D3:D26 =COUNT(Range1, Range2,…): to count the number of values within one/many ranges. Task 2: count the number of missing values in D3:D26 =COUNTBLANK(Range): will count all the empty cells within ONE given range. Task 3: count the number of last names in A3:A26 =COUNTA(): count all the cells having a value in whatever types. Note: =COUNT() only work with numerical numbers; =COUNT(A3:A26) gives you 0 Task 1: Get the initials of the students in Column C o =LEFT(A2,1)&LEFT(B2,1) Task 2: Get the full names of the students (LastName FirstName) in Column D o =A2&" "&B2 Task 3: Calculate the average marks in Mid1: Final Exam o J2: =AVERAGE(F2:I2) Note: warning message Formula Omits Adjacent Cells, because StudentID is also considered as a number in Excel. Task 4: In column K, display the integer part of the average in column J o =INT(J2) Task 5: Display the rounded value of the average in column J, using the number of decimal places in O2 o =ROUND(K4,$O$2) Taks 6: Count the number of students in Column D (Full Name) o =COUNTA(D2:D25) Task 7: calculate corresponding Minimum values in columns F:J (Mid1:Average) o =MIN(F2:F25) Task 8: Calculate Max, Average, Sum, missing marks and number of marks in each column o =AVERAGE(F2:F25) o =SUM(F2:F25) o =COUNTBLANK(F2:F25) o =COUNT(F2:F25) Task 9: Display the results in J27:J30 in 2 decimals, and Center the content in F27:J32 o ribbon Home > panel Number to control the displayed decimals. o ribbon Home > panel Alignment to control the display. Part 4 – Formulas with Date and Time functions Dealing with dates File: Module1 – Part 4 Formulas with Date and Time functions.xlsx Worksheet: Using Date functions To enter a date in a cell: • American: MM/DD/YYYY • French: DD/MM/YYYY Note: o Excel dates start on 01/01/1900, to the end 12/31/9999. o If Excel recognizes it is a date, it will automatically align to the right. o Try: 1/24/2000, 24/01/2000 o when entering a fraction, 1/3, excel will regard it as a date 3-Jan. You need =1/3 for the value. In the system, the date will be stored as a serial number. Try to see a date in number format. Task 1: Todays date o =TODAY() Task 2: Todays date and time o =NOW() Task 3: Return the Day, Month, Year, and day of the week of Cell B3 o =DAY(B3), =MONTH(B3), =YEAR(B3), =WEEKDAY(B3) Note: =WEEKDAY(Date, [option]) default Sunday being number 1. Task 4: Create a date from values of Day (13), Month (3), and Year (2018) o =DATE(DD,MM,YYYY) Task 5: how many days between 01/01/2020 and 01/02/2020 (including start and end dates) o =B14 – B13 +1 Task 6: Calculate the date that X days after a certain date. o Adding one day to the date, =B13+1 Task 7: calculate the number of years between two dates. o =DATEDIF(B17,B18,"Y") Dealing with times To insert a time (in 24h format): HH:MM:SS or HH:MM Like the date, Excel will convert it into a series of numbers. You can check the associated value in Number format, e.g., 12:08 0.51. Task: Calculate duration between two times (B5). o =B3 – B2 Task: Display time now in a different format. Task: Extract different part of a time o E2: =NOW(), then change format to Time o E3: =HOUR(E2) o E4: =MINUTE(E2) o E5: =SECOND(E2) o Click Calculate Now to update Task: Build time from Hour, Minutes and Secondsin G2:G5 o =TIME(H2,H3,H4) Task: Calculate the duration between the corresponding start and end time in columns B and C. o In D9, =C9 – B9 then Change the format to 13.30 to remove AM and Propagate by Tips to propagate: o Double click the copy handle OR o Select the D9:D24, then press shortcut Ctrl + D OR o Select the D9:D24, select ribbon Home Panel Editing Down Task: calculate total duration in D9:D24 o =SUM(D9:D24) Note: If you see 15:10, it is wrong! Because it exceeds the 24hr. A wrong display format! Change to 37:30:55! Date format Task: calculate total payment when the pay per hour is 30$ Wrong way: only multiply the total duration and the hourly pay Excel understands the duration as 1.62 days (check it in Number format). We need to multiply it by 24 hr/day. o =D25*D26*24
COMM 1000 Critical Thinking Assignment Part C Final Draft Purpose: 1) Apply your critical thinking skills to engage with a topic. Course Learning Outcomes worked towards: 1) Apply a set of strategies to create short pieces of organized, coherent, clear, and concise writing with an understanding of one’s audience and purpose. 2) Apply critical reading strategies to improve comprehension of text 3) Apply basic understanding of critical thinking skills to engage with a topic. Value: 15% (of your total mark) Due Date: Week 13 on the class day at 11:59 pm Assignment Instructions: 1. Choose one of the options below. Option 1 Imagine that you work at a resort. This resort has recently been sold, and the new owners want to make their mark in the tourism industry. The new owners want guest chefs to come to the resort to introduce new cuisines and/or culinary ideas to the restaurants at the resort. They think specific guest chefs can attract tourists. The guest chef would stay at the resort for about 2 weeks. The new owners have asked each employee to recommend a guest chef for the resort. Your job as an employee at the resort is to recommend a guest chef. The recommendation could show how that guest chef could draw tourists to the resort. In about 750 words recommend a guest chef to the new resort owners. Your recommendation should be persuasive as you explain to the new owners why your choice of guest chef would attract tourists to the resort. In your recommendation, be sure to explain why the guest chef is personally meaningful and relevant to you. Your response should have a distinct introduction, body, and conclusion. In your introduction, you should have a clear and logical thesis/ main message. In your body, you should have relevant supporting points, logical reasoning, and appropriate examples to back up your points and overall main message. Do not forget to cite your sources (= intext citations and the matching full references). The conclusion should include the importance/significance of your choice of chef. You will need to include at least 2 sources (but you can have more than 2) to help you with your recommendation. These sources should be from 2023-2024. For this assignment, references can be articles (from newspapers, magazines, or regular websites), Encyclopedia Britannica articles, ebooks, audiobooks, podcasts, videos, or social media posts, but not academic journal articles (= no articles that have a volume number, an issue number or a doi). You can use (but don’t have to) the sources from the Paragraph assignment, and Critical Thinking Parts A & B for this option If you find a reference that you want to use that was posted before 2023, or has no date of publication, send me an email with a link to the source and explain why/how you want to use this reference. I will decide if ‘other’ references can be used on a case-by-case basis. Cite all of the sources you use in APA 7 formatting for intext citations and the matching full references. Do not use hyperlinks in your referencing. Option 2 Imagine this scenario involving food delivery. You order food to be delivered to your home. You gave what you consider a reasonable tip for the delivery person in the order. A delivery person contacts you and demands an extra tip to deliver the food. Would you pay the extra tip? In about 750 words, say whether you would give the delivery person another tip to deliver your food and why. The focus of this option should be what you would do and why if a delivery driver demanded an extra tip to deliver your food. You can mention the tipping situation for food delivery people, but that should support why you would tip the delivery person or not. Your response should have a distinct introduction, body, and conclusion. In your introduction, you should have a clear and logical thesis/ main message. In your body, you should have relevant supporting points, logical reasoning, and appropriate examples to back up your points and overall main message. Do not forget to cite your sources of information and examples (= intext citations and the matching full references). The conclusion should include the importance/significance of whether you would give the extra tip or not. For option 2, you must include information from at least 2 articles from the Food delivery & tipping 2023+ wakelet. (Access the wakelet by clicking on the underlined title). You can use more than 2 articles from the wakelet if you want. You can only use sources that are found in the wakelet for this option. The use of other sources will result in 0/15 for this assignment. Cite all of the sources you use in APA 7 formatting for intext citations and the matching full references. Do not use hyperlinks in your referencing. Use the outline from Critical Thinking: Part B (5%) to create the final version of your assignment 2. Format your essay in APA style. This includes the cover page, page numbers, and documenting your sources – including intext citations and the matching full references
COMP1649 (2024/25) Human Computer Interaction and Design Learning Outcomes: 1 Deploy theory, design principles, tools and methodologies to implement andevaluate human- computer interactions; 2 Carry out design research to inform. development of systems and applications; 3 Construct and create prototypes of human-computer interactions; 4 Demonstrate the origins of ideas by correctly citing and referencing sources used in the work. Coursework Submission Requirements • An electronic copy of your work for this coursework must be fully uploaded on the Deadline Date using the link on the coursework Moodle page for COMP1649. • For this coursework you must submit a single PDF document. In general, any text in the document must not be an image (i.e. must not be scanned) and would normally be generated from other documents (e.g. MS Office using "Save As .. PDF"). An exception to this is hand written mathematical notation, but when scanning do ensure the file size is not excessive. • For this coursework you must also upload your prototype file. • There are limits on the file size (see the relevant Moodle page). • Make sure that any files you upload are virus-free and not protected by a password or corrupted otherwise they will be treated as null submissions. • You must NOT submit a paper copy of this coursework. • All courseworks must be submitted as above. Under no circumstances can they be accepted by academic staff. • All mid-fidelity prototypes for this module must be submitted as Axure RP file unless agreed with the module leader otherwise. Submissions of prototypes submitted in other formats or as proprietary file types from other prototyping tools will not be accepted and marks for the prototype will be reduced to 0. The University website has details of the current Coursework Regulations,including details of penalties for late submission, procedures for Extenuating Circumstances, and penalties for Assessment Offences. See https://www.gre.ac.uk/student-services/exams/regs and the Academic Regulations for Taught Awards. Detailed Specification Design brief Choose one of the following topic areas for your coursework: A. Design a digital application (e.g. a mobile app) for homeless individuals in London to suit basic needs. Potential features may include: Finding locations and times for free meals, shower and toilet facilities, and contacting relevant services (job finding, shelters) etc. B. Design a digital application (e.g. a mobile app) for outdoor rock climbers in the UK. Potential features may include: logging climbs (recording and tracking ascents, viewing logs), social features for contacting and information sharing with fellow sport climbers, and local weather forecasts. Wearables connected to an app could be considered. C. Design a digital application (e.g. a tablet app) for children in the UK to explore animals, trees and plants in the woods. Potential features may include: Nature identification (e.g. recording bird sounds), ticking off trees that have been seen, and recording routes taken. You have been commissioned to write a report and create a prototype for a new interactive product for one of the above products and target groups. Investigate the needs and context of the chosen target group and product, and decide on two to three main features, supported by your literature research. The scope of the interactive prototype should focus on two to three main areas. You are asked to create a proof of concept for the interactions of this system to see if users find it usable and desirable. The basic brief is open for interpretation, and you can and should design desirable interactions as you see fit based on your background readings and your research activities. Interactive prototype You need to create a mid-fidelity prototype of the application that enables people to experience at least the core user journeys/scenarios (two or three) that are available in your application in an interactive manner. This prototype should be developed in Axure RP10, unless agreed otherwise with the module leader. You are required to describe the conceptual design and provide a description and visualisation of the product and its components and interactions in the report. You need to submit an interactive digital prototype demonstrating the interface and interactions of your application and explain how a user interacts with its components. Your design and research activities need to be in alignment with your target group and justifications for all your assumptions and design decisions need to be provided. Report At the beginning of your report, you need to state your choice of topic from the above options. In the coursework report, you document your research and design activities, and the required future research study and other future work for the product. This includes a review of relevant literature that informed your design, a discussion of the conceptual design for the product, and a discussion of how design principles will be applied. The report will also discuss your (design) process of developing the interactive mid-fidelity prototype and how relevant HCI theory has been implemented. A plan for an empirical research study should be proposed to investigate a research question or hypothesis, and the conclusion should also detail other aspects of future work required. More details can be found in the assessment criteria below. You may also want to consult the annotated table of contents available on the COMP1649 Moodle page to help you structure your report. Your report needs to be professionally and academically written and structured, based on your own research and reading, and written by yourself using appropriate in-text citations and referencing. This includes the demonstration of English language proficiency, appropriate level of detail, professional formatting of the report, and the writing should be supported by at least 8 relevant academic references (journal papers, conference papers, academic books - not blogs or online tutorials etc.). References and in-text citations should be formatted in Harvard style. The report word limit is 3000 words. If the submitted work exceeds the limit by more than 10%, marks will be reduced. Deliverables o Report of 2000-3000 words uploaded as a pdf file. o Mid-fidelity prototype uploaded as .rp. The prototype should be submitted as an Axure RP file unless otherwise agreed with the module leader. Assessment Criteria Report Professional writing style, English language proficiency, writing with appropriate level of detail, professional report formatting, sufficient and appropriate referencing in Harvard style. of academic sources (e.g. journal papers, conference papers, academic books) throughout the report. A minimum of 8 sources is expected. 5% A review of relevant and appropriate HCI background literature written in your own words and appropriately referenced, to inform. the design of the product and to generate requirements. The relevant background research (e.g. related work, HCI literature in relation to the product’s context, interaction design theory, cognitive psychology etc.) should support generating requirements for the proposed solution. It should be made clear which academic sources have been used and how they were retrieved. 20% The product design consisting of A) A discussion of the product idea (conceptual design) explaining the components of the product and how the user will interact with the product, and how requirements will be met, and B) The design principles (by Don Norman) and their application to the coursework product are discussed. A brief discussion for each principle/concept and suitable visual representations should be included. 15% A detailed proposal for an empirical HCI research study that uses your interactive prototype. In this proposal, you need to describe and justify the details for a research study including the research question(s) or hypothesis that your research study attempts to investigate, who the participants of your study will be, how the study will be run, the data collection, and how you will analyse the data. You do not need to run the study but you need to create all necessary material and documentation that are required for a usability expert to run the study. 20% A conclusion providing critical reflections on the limitations of the work that has been carried out and a discussion of potential future work if the project would be developed further. The conclusion needs to go beyond repeating what has been said elsewhere and show a clear vision in the context of HCI of what the next steps for such a project would be. 10% Mid-fidelity prototype of an interactive product Clear links between the coursework report and the prototype with design decisions explicitly documented and justified in the report. There is evidence of the effective and successful application of HCI theory and design principles to create a prototype that can be used to test core assumptions of your design and that is suitable for researchers and designers to test and evaluate the product. The implementation of design research, theory, and principles is evident in both the report and the prototype. 30%
ECM3422 – Computability and Complexity Academic Year: 2024/25 Title: Continous Assessment Submission deadline: 2024-11-27 This assessment contributes 20% of the total module mark and assesses the following intended learning outcomes: • Module Specific Skills and Knowledge: – explain what is meant by a general model of computation and work with some specific examples of such models; – describe the mathematical basis of the theory of computability and complexity; • Discipline Specific Skills and Knowledge: – appreciate the power of abstraction to support a general understanding of some subject matter; – appreciate the role of theoretical understanding in underpinning disciplined and responsible prac- tice. • Personal and Key Transferable / Employment Skills and Knowledge: – approach problems analytically at an appropriate level of abstraction. This is an individual assessment, and you are reminded of the University’s Regulations on Collaboration and Plagiarism. You must avoid plagiarism, collusion and any academic misconduct behaviours. Further details about Academic Honesty and Plagiarism can be found at https://ele.exeter.ac.uk/course/ view.php?id=1957. This course work consists out of two questions. You can get up to 100 marks in total split across two exercises: 1. A manual simulation of a multi tape Turing Machine (5h, 30 marks) 2. An implementation of a simulator of a multi tape Turing Machine using a single tape Turing Machine (15h, 70 marks) The CA comes with template python files which you can download from the assessment section on the ELE page. The file README.md contains detailed instructions on how to run the tests. Before submitting your coursework make sure the project compiles and the tests provided in the template succeed. Implementations that cannot run the provided test suite, will receive zero marks. Use of GenAI tools in Continous Assessment for ECM3422 - Computability and Complexity The University of Exeter is committed to the ethical and responsible use of Generative AI (GenAI) tools in teaching and learning, in line with our academic integrity policies where the direct copying of AI-generated content is included under plagiarism, misrepresentation and contract cheating under definitions and offences in TQA Manual Chapter 12.3. To support students in their use of GenAI tools as part of their assessments, we have developed a category tool that enables staff to identify where use of Gen AI is integrated, supported or prohibited in each assessment. This assessment falls under the category of AI-supported. You can find further guidance on using GenAI critically, and how to use GenAI to enhance your learning, on Study Zone digital. When submitting your assessment, you must include the following declaration, ticking all that apply: AI-supported/AI-integrated use is permitted in this assessment. I acknowledge the following uses of GenAI tools in this assessment: • I have used GenAI tools for developing ideas. • I have used GenAI tools to assist with research or gathering information. • I have used GenAI tools to help me understand key theories and concepts. • I have used GenAI tools to identify trends and themes as part of my data analysis. • I have used GenAI tools to suggest a plan or structure for my assessment. • I have used GenAI tools to give me feedback on a draft. • I have used GenAI tool to generate image, figures or diagrams. • I have used GenAI tools to proofread and correct grammar or spelling errors. • I have used GenAI tools to generate citations or references. • Other: [please specify] I declare that I have referenced use of GenAI outputs within my assessment in line with the University referencing guidelines. Please note: Submitting your work without an accompanying declaration, or one with no ticked boxes, will be considered a declaration that you have not used generative AI in preparing your work. If a declaration sheet cannot be uploaded as part of an assignment (i.e. at the start of an essay), students understand that by submitting their assessment that are confirming they have followed the assessment brief and guidelines about GenAI use. Instructions Task 1: Simulating a Multi-Tape Turing Machine on a Single-Tape Turing Machine For the following exercise you should manually simulate a given multi-tape Turing machine using a corre- sponding single-tape Turing machine. Definition of the Multi-Tape Turing Machine The multi-tape Turing machine M to be simulated is defined as follows: M = (Q; Σ; Γ; δ ; q0; □; {q5 }) with • Q = {q0; ...; q5 } • Σ = {0; 1} • Γ = {0; 1; □ } M has three tapes (and three read/write heads). Hence, the transition function has the form.: δ : Q × (Γ × Γ × Γ) → P(Q × (Γ × Γ × Γ) × ({L; R; N } × {L; R; N } × {L; R; N })) . The triples (Γ × Γ × Γ) denote the symbols on the first, second, and third tape and ({L; R; N } × {L; R; N } × {L; R; N }) are the movements of the first, second, and third read/write head. The transition function is defined as follows: Task Description (30 marks) Assume M, is a corresponding single-tape Turing machine which is started with input 011010010 For this task you need to determine the state of the tape for M, at different points in time. The state of the tape can be described by listing the elements of Σ* currently on the tape. Note that you do not need to specify the state of M, nor the position of the head but only the state of the tape. 1. What will the tape look like after initialization (i.e., when M reaches q0 )? (5 marks) 2. What will the tape look like when M reaches q2 ? (5 marks) 3. What will the tape look like when M reaches q3 ? (5 marks) 4. What will the tape look like when M reaches q4 ? (5 marks) 5. What will the tape look like when M reaches q5 ? (5 marks) 6. What will the tape look like at the end of the execution? (5 marks) Task 2: Implementing a Simulator for Multi-Tape Turing Machines using a given Single-Tape Turing Machine For this exercise you need to implement a multi-tape Turing machine using a given single-tape one. To this end we provide you with a Python implementation of a single-tape Turing machine. Implementation of the Single-Tape Turing Machine The single-tape Turing machine is implemented in class TuringMachine in the file TuringMachine.py. The class contains, amongst other things, the following elements: • A string variable blank_symbol which stores the element used to denote a blank symbol. • A constructor __init__ which initializes the machine. It takes the following parameters: – initial_state: A string representing the initial state. – final_states: A set of strings representing the final states. – head_position: The start position of the head on the tape. – tape_string: A string representing the input. • A method is_final which takes a state as input and returns true if the state is a final state. • An abstract method transition with two parameters: a state and a string. The method is supposed to implement the transition function. It must return a triple in which the first component is a string representing the result state, the second component is a string representing the output character, and the third element is either “L”, “R”, or “N” to denote the movement of the head. • A method run which executes the machine by using the abstract transition method. • A method get_tape_string to return a formatted string of the tape. • A method get_raw_tape to return a raw representation of the tape in which leading and trailing blanks are removed. • A method checkhead which takes an integer and checks if the head is currently on that position. Counting starts from the first non-blank element position. • A method is_blank which takes a string and checks if it is the blank symbol. Task Description (70 marks) You need to implement the multi-tape Turing machine by inheriting from the class TuringMachine. We provide also a template for this: Class MTTuringMachine in file MTTuringMachine.py. The class contains the following elements: • A constructor __init__ which takes the following parameters: – tapes: An integer to denote the number of tapes. – initial_state: A string to denote the initial state. – final_states: A set of strings to denote the final states. – tape_string: A string to denote the input. The constructor should be implemented by calling the constructor of the single-tape Turing machine. You need to implement this constructor. There is a TODO marker in the provided template which should be replaced by your implementation. • An abstract function transitionm with two parameters: a state and a tuple of strings. This method is supposed to provide the implementation of the transition function for the multi-tape machine (i.e. it will be implemented by users of the simulator). This function is provided in the template and should not be modified. • An implementation of the transition method. This method should use the transition function of the multi-tape Turing machine (transitionm) to implement the transition function for the single-tape Turing machine (remember that transition is an abstract method in class TuringMachine). You need to implement this method. There is a TODO marker in the provided template which should be replaced by your implementation. The class can use the abc library for abstract methods and the re library for regular expressions but should not use any other Python modules (libraries). Remark. We provide a test implementation of a simple multi-tape Turing machine, extending the class MTTuringMachine. The test file is called Tests .py and contains a class myTM which implements a multi- tape turing machine using MTTuringMachine. Moreover, it contains a class TestStringMethods which provides a method test_1 which executes a possible test case. The tests can be executed by running Tests .py using Python 3.12. We strongly recommend that you use it to test if your implementation fulfills the basic functional requirements. Implementations that cannot be executed against this test suite will receive zero marks. Note that for the final marking we will use additional tests. Marking scheme For each criteria we reward marks if the implementation generally satisfies the criteria, and we provide additional marks if edge cases are considered. • Correct initialization: The single-tape Turing machine is properly initialized according to the specifi- cation of the multi-tape Turing machine (general: 10 marks, edge cases: 10 marks) • Correct transition: The single-tape Turing machine implements the correct sequence of transitions specified by the multi-tape Turing machine (general: 20 marks, edge cases: 20 marks) • Correct finalization: The single-tape Turing machine properly finalizes the computation (general: 5 marks, edge cases: 5 marks)
In this assignment, you will implement k-means clustering and use it to construct a multi-label classifier to determine the variery of wheat. For the dataset, we use ”seeds” dataset from the machine Learning depository at UCI: https://archive.ics.uci.edu/ml/datasets/seedsDataset Description: From the website: ”… The examined group comprised kernels belonging to three different varieties of wheat: Kama, Rosa and Canadian, 70 elements each, randomly selected for the experiment…”There are 7 (continuous) features) F = {f1, . . . , f7} and a class label L (Kama: 1, Rosa: 2, Canadian: 3). 1. f1: area A 2. f2: perimeter P 3. f3: compactness C = 4πA/P2 4. f4: length of kernel, 5. f5: width of kernel, 6. f6: asymmetry coefficient 7. f7: length of kernel groove.8. L: class (Kama: 1, Rosa: 2, Canadian: 3) For the first question, you will choose 2 class labels as follows. Take the last digit in your buid and divide it by 3. Choose the following 2 classes depending on the remainder R: 1. R = 0: class L = 1 (negative) and L = 2 (positive) 2. R = 1: class L = 2 (negative) and L = 3 (positive) 3. R = 2: class L = 1 (negative) and L = 3 (positive) Question 1: Take the subset of the dataset containing your two class labels. You will use random 50/50 splits for training and testing data.1. implement a linear kernel SVM. What is your accuracy and confusion matrix? 2. implement a Gaussian kernel SVM. What is your accuracy and confusion matrix? 3. implement a polynomial kernel SVM of degree 3. What is your accuracy and confusion matrix? Question 2: Pick up any classifier for supervised learning (e.g. kNN, logistic regression, Naive Bayesian, etc).1. use this classifier to your dataset. What is your accuracy and confusion matrix? 2. summarize your findings in a table below and discuss your results Model TP FP TN FN accuracy TPR TNR linear SVM Gaussian SVM polynomial SVM your classifierQuestion 3: Take the original dataset with all 3 class labels. 1. for k = 1, 2, . . . , 8 use k-means clustering with random initialization and defaults. Compute and plot distortion vs k. Use the ”knee” method to find the best k. 2. re-run your clustering with best k clusters. Pick two features fi and fj at random (using python, of course) and plot your datapoints (different color for each class and centroids) using fi and fj as axis. Examine your plot. Are there any interesting patterns? 3. for each cluster, assign a cluster label based on the majority class of items. For example, if cluster Ci contains 45% ofclass 1 (”Kama” wheat), 35% of class 2 (”Rosa” wheat) and 20% of class 3 (”Canadian” wheat), then this cluster Ci is assigned label 1. For each cluster, print out its centroid and assigned label. 4. consider the following multi-label classifier. Take the largest 3 clusters with label 1, 2 and 3 respectively. Let us call these clusters A, B and C. For each of these clusters, you know their means (centroids): µ(A), µ(B) and µ(C). We now consider the following procedure (conceptually analogous to nearest neighbor with k = 1): for every point x in your dataset, assign a label based on the label on the nearest (using Euclidean distance) centroid of A, B or C. In other words, if x is closest to center of cluster A, you assign it label 1. If x is closest to center of cluster B, you assign it class 2. Finally, if x is closest to center of cluster C, you assign it class 3. What is the overall accuracy of this new classifier when applied to the complete data set?5. take this new classifier and consider the same two labels that you used for SVM. What is your accuracy and confusion matrix? How does your new classifier (from task 4) compare with any classifiers listed in the table for question 2 above?
In this assignment, we will compare Naive Bayesian and Decision Tree Classification for identifying normal vs. non-normal fetus status based on fetal cardiograms. For the dataset, we use ”fetal cardiotocography data set” at UCI: https://archive.ics.uci.edu/ml/datasets/Cardiotocography Dataset Description: From the website: ”2126 fetal cardiotocograms (CTGs) were automatically processed and the respective diagnostic features measured. The CTGs were also classified by three expert obstetricians and a consensus classification label assigned to each of them. Classification was both with respect to a morphologic pattern (A, B, C. …) and to a fetal state (N, S, P). Therefore the dataset can be used either for 10-class or 3-class experiments.” We will focus on the ”fetal state”. We will combine labels ”S” (suspect) and ”P” (pathological) into one class ”A” (abnormal). We will focus on predicting ”N” (normal) vs. ”A” (”Abnormal”). For a detailed description of features, please visit the above website. The data is an Excel (not csv) file. For ways to process excel files in Python, see https://www.python-excel.org/You will use the following subset of 12 numeric features: 1. LB – FHR baseline (beats per minute) 2. ASTV – percentage of time with abnormal short term variability 3. MSTV – mean value of short term variability 4. ALTV – percentage of time with abnormal long term variability 5. MLTV – mean value of long term variability 6. Width – width of FHR histogram 7. Min – minimum of FHR histogram 8. Max – Maximum of FHR histogram 9. Mode – histogram mode 10. Mean – histogram mean 11. Median – histogram median 12. Variance – histogram variance You will consider the following set of 4 features depending on your facilitator group.• Group 1: LB, ALTV, Min, Mean • Group 2: ASTV, MLTV, Max, Median • Group 3: MSTV, Width, Mode, Variance • Group 4: LB, MLTV, Width, Variance For each of the questions below, these would be your features.Question 1: 1. load the Excel (”raw data” worksheet) data into Pandas dataframe 2. combine NSP labels into two groups: N (normal – these labels are assigned) and Abnormal (everything else) We will use existing class 1 for normal and define class 0 for abnormal.Question 2: Use Naive Bayesian NB classifier to answer these questions: 1. split your set 50/50, train NB on Xtrain and predict class labels in Xtest 2. what is the accuracy? 3. compute the confusion matrixQuestion 3: Use Decision Tree to answer these questions: 1. split your set 50/50, train NB on Xtrain and predict class labels in Xtest 2. what is the accuracy? 3. compute the confusion matrixQuestion 4: Recall that there are two hyper-parameters in the random forest classifier: N – number of (sub)trees to use and d – max depth of each subtreeUse Random Forest classifier to answer these questions: 1. take N = 1, . . . , 10 and d = 1, 2, . . . , 5. For each value of N and d, split your data into Xtrain and Xtest, construct a random tree classifier (use ”entropy” as splitting criteria – this is the default) Train you r classifier on Xtrain and compute the error rate for Xtest2. plot your error rates and find the best combination of N and d. 3. what is the accuracy for the best combination of N and k? 4. compute the confusion matrix using the best combination of N and dQuestion 5: Summarize your results for Naive Bayesian, decision tree and random forest in a table below and discuss your findings. Model TP FP TN FN accuracy TPR TNR naive bayesian decision tree random forest
In this programming project, you will write an OCaml module whose functions parse Lisp thing’s from a file, and return the internal representations of those thing’s. It will use the token scanner from Lab 9, in a module called Scanner. If we have a function that reads Lisp thing’s, a function that evaluates Lisp thing’s, and a function that prints Lisp thing’s, then we could put them all together to make a complete Lisp system. Writing the evaluator will be the subject of the next few lectures.1. Theory.In formal language theory, a language is a set of strings; a string is a sequence of tokens. A grammar is a mathematical description of a language that tells which strings are in the set, and which strings are not. One way to specify a grammar is to use mathematical rules, but we won’t do that here. Instead, we’ll use a directed graph called a syntax diagram. A syntax diagram for Lisp thing’s is shown below.Every syntax diagram has a name: the name of this diagram is thing. It has exactly one arrow that lets you enter the diagram on the left, and exactly one arrow that lets you exit the diagram on the right. By following arrows from left to right, going all the way through the diagram, you can tell what sequences of tokens can be thing’s. The box labeled thing stands for a Lisp thing. The diagram is recursive, because it is defined in terms of itself: there is a box labeled thing inside the diagram labeled thing. The box labeled number is a Lisp number token (from Lab 9). It’s a sequence of one or more digits, ‘0’ through ‘9’, preceded by an optional minus sign ‘−’. The box labeled symbol is a Lisp symbol token (also from Lab 9). It’s a sequence of one or more characters other than blanks, newlines, and parentheses. There is no box labeled nil, because it’s simpler to pretend that nil is a symbol, even though it really isn’t (see below). Here are some examples of thing’s that are described by the diagram. A number, like 100, is a thing, because we can start on the left, follow arrows to the box labeled number, and then follow arrows out of the diagram again. A symbol, like hello, is also a thing, because we can start on the left, follow arrows to the box labeled symbol, and then follow arrows out of the diagram. An empty list, like (), is a thing, because we can follow an arrow to the circle labeled ‘(’, follow an arrow to the circle labeled ‘)’, and then follow an arrow out of the diagram. In Lisp, () is just another notation for nil (see below). A list, like (a b c), is a thing, because we can follow an arrow to the circle labeled ‘(’, and then to the box labeled thing. We imagine that a copy of the diagram thing appears in place of that box. If we follow arrows through that copy, then we find that a is also a thing. If we go around the loop, back to the box labeled thing, we find in the same way that b is another thing, and if we go around the loop again, we find that c is a thing as well. When we exit the loop, we follow an arrow through a circle labeled ‘)’, and then follow yet another arrow out of the diagram. We could show that nested lists like ((a) b c) and (a (b c)) are thing’s too, by following arrows through the diagram in the same way. And we could show that something like ‘)x(()5(’ is not a thing, because there is no way to follow arrows through the diagram given its tokens.2. Implementation.For this project, you must write an OCaml module called Parser, whose type is the OCaml signature Parsers. (A parser is a procedure that reads a series of tokens and constructs a representation of what the tokens stand for.) The module Parser will use functions defined in the module Scanner from Lab 9. Although Parser may contain many functions, only two OCaml objects must be visible outside it: the exception Can'tParse, and the function makeParser, both of which are described below.Here are some hints about how to write these functions. The scanner and the parser are designed according to similar rules, as follows.To make some of these rules work, it is necessary to skip tokens after they are read. If nextToken is the name of the scanner created by makeScanner, then we can skip a token by writing token := nextToken (). For example, after nextThing reads a SymbolToken, it must skip that token in this way.3. Examples.The file things.txt on Canvas contains a series of example Lisp expressions. They are the same ones that were used to test the printing function from Lab 10. The file testsP2.ml on Canvas contains a series of calls to a parser created by makeParser. Each call reads the next Lisp expression from things.txt, converts it to an OCaml object, and prints that object. You can use things.txt and testsP2.ml to test whether your parser works. However, unlike the tests that come with lab assignments, the tests in testsP2.ml are not worth points! The TA’s will grade this project by reading your code, not by counting how many tests succeed and fail.4. Deliverables.Unlike the lab assignments, YOU ARE NOT ALLOWED TO WORK WITH A PARTNER ON THIS PROJECT. Although you may discuss the project with others in a general way, IT MUST BE WRITTEN ENTIRELY BY YOURSELF. The project is worth 50 points, and will be due at 11:55 PM on December 8, 2021. The file parser.ml, available on Canvas, contains definitions for the OCaml type thing and the OCaml module Scanner, both from previous labs. It also has space for you to put your code for Parser, the module that you must write for this project. Write your code in that space and submit a copy of parser.ml with your code in it. If you do know know how or where to submit this file, then please ask your lab TA. DOUBLE CHECK to make sure you have submitted the correct file, both BEFORE AND AFTER you turn it in.
In this programming project, you will write an OCaml module whose functions parse Lisp thing’s from a file, and return the internal representations of those thing’s. It will use the token scanner from Lab 9, in a module called Scanner. If we have a function that reads Lisp thing’s, a function that evaluates Lisp thing’s, and a function that prints Lisp thing’s, then we could put them all together to make a complete Lisp system. Writing the evaluator will be the subject of the next few lectures.1. Theory.In formal language theory, a language is a set of strings; a string is a sequence of tokens. A grammar is a mathematical description of a language that tells which strings are in the set, and which strings are not. One way to specify a grammar is to use mathematical rules, but we won’t do that here. Instead, we’ll use a directed graph called a syntax diagram. A syntax diagram for Lisp thing’s is shown below.Every syntax diagram has a name: the name of this diagram is thing. It has exactly one arrow that lets you enter the diagram on the left, and exactly one arrow that lets you exit the diagram on the right. By following arrows from left to right, going all the way through the diagram, you can tell what sequences of tokens can be thing’s. The box labeled thing stands for a Lisp thing. The diagram is recursive, because it is defined in terms of itself: there is a box labeled thing inside the diagram labeled thing. The box labeled number is a Lisp number token (from Lab 9). It’s a sequence of one or more digits, ‘0’ through ‘9’, preceded by an optional minus sign ‘−’. The box labeled symbol is a Lisp symbol token (also from Lab 9). It’s a sequence of one or more characters other than blanks, newlines, and parentheses. There is no box labeled nil, because it’s simpler to pretend that nil is a symbol, even though it really isn’t (see below). Here are some examples of thing’s that are described by the diagram. A number, like 100, is a thing, because we can start on the left, follow arrows to the box labeled number, and then follow arrows out of the diagram again. A symbol, like hello, is also a thing, because we can start on the left, follow arrows to the box labeled symbol, and then follow arrows out of the diagram. An empty list, like (), is a thing, because we can follow an arrow to the circle labeled ‘(’, follow an arrow to the circle labeled ‘)’, and then follow an arrow out of the diagram. In Lisp, () is just another notation for nil (see below). A list, like (a b c), is a thing, because we can follow an arrow to the circle labeled ‘(’, and then to the box labeled thing. We imagine that a copy of the diagram thing appears in place of that box. If we follow arrows through that copy, then we find that a is also a thing. If we go around the loop, back to the box labeled thing, we find in the same way that b is another thing, and if we go around the loop again, we find that c is a thing as well. When we exit the loop, we follow an arrow through a circle labeled ‘)’, and then follow yet another arrow out of the diagram. We could show that nested lists like ((a) b c) and (a (b c)) are thing’s too, by following arrows through the diagram in the same way. And we could show that something like ‘)x(()5(’ is not a thing, because there is no way to follow arrows through the diagram given its tokens.2. Implementation.For this project, you must write an OCaml module called Parser, whose type is the OCaml signature Parsers. (A parser is a procedure that reads a series of tokens and constructs a representation of what the tokens stand for.) The module Parser will use functions defined in the module Scanner from Lab 9. Although Parser may contain many functions, only two OCaml objects must be visible outside it: the exception Can'tParse, and the function makeParser, both of which are described below.Here are some hints about how to write these functions. The scanner and the parser are designed according to similar rules, as follows.To make some of these rules work, it is necessary to skip tokens after they are read. If nextToken is the name of the scanner created by makeScanner, then we can skip a token by writing token := nextToken (). For example, after nextThing reads a SymbolToken, it must skip that token in this way.3. Examples.The file things.txt on Canvas contains a series of example Lisp expressions. They are the same ones that were used to test the printing function from Lab 10. The file testsP2.ml on Canvas contains a series of calls to a parser created by makeParser. Each call reads the next Lisp expression from things.txt, converts it to an OCaml object, and prints that object. You can use things.txt and testsP2.ml to test whether your parser works. However, unlike the tests that come with lab assignments, the tests in testsP2.ml are not worth points! The TA’s will grade this project by reading your code, not by counting how many tests succeed and fail.4. Deliverables.Unlike the lab assignments, YOU ARE NOT ALLOWED TO WORK WITH A PARTNER ON THIS PROJECT. Although you may discuss the project with others in a general way, IT MUST BE WRITTEN ENTIRELY BY YOURSELF. The project is worth 50 points, and will be due at 11:55 PM on December 8, 2021. The file parser.ml, available on Canvas, contains definitions for the OCaml type thing and the OCaml module Scanner, both from previous labs. It also has space for you to put your code for Parser, the module that you must write for this project. Write your code in that space and submit a copy of parser.ml with your code in it. If you do know know how or where to submit this file, then please ask your lab TA. DOUBLE CHECK to make sure you have submitted the correct file, both BEFORE AND AFTER you turn it in.
SEMESTER 1 2024/25 COURSEWORK BRIEF: Module Code: MANG1003 Assessment: Individual Coursework Weighting: 70% Module Title: Introduction to Management Submission Due Date: @ 16:00 Thursday 12th December 2024 (Wk 11) Word Count: 1500 This assessment relates to the following module learning outcomes: A. Knowledge and Understanding A2. Tools and techniques used within General Management A4. How the role of management can affect the performance of an organisation B. Subject Specific Intellectual and Research Skills B1. Reflect on management theory and practice through examining the nature of management and human activity C. Transferable and Generic Skills C2. Synthesise information from a range of sources to answer a question C3. Demonstrate effective written and/or oral communication Coursework Brief: Please read this brief multiple times throughout the semester to ensure you are clear on what is required. Doing everything here will ensure you get the best mark you can. You are to write an individual reflective report of 1500 words (excluding reference list) on your experience of working in a team for the MANG1003 group assignment. You are expected to use all 5 stages of Tuckman and Jensen’s (1977) model in your analysis, and you should also incorporate other relevant theories on teamwork, roles, motivation, communication, and conflict to explain any issues you may have experienced. You can reflect on both negative and positive aspects of the experience. If upon reflection, your team was functioning well then you should make suggestions as to why that was the case. You should conclude your reflective report with ‘My THREE key learnings about teamwork are...’ You need to state here what you have learned and how you might use this knowledge in similar future situations. These should naturally flow and follow from your essay. In the report, you should illustrate your key points with examples from your group work and support your discussions on group work with studied references. You are strongly advised to read the notes below that give for tips on writing and structuring your work. The grade descriptors for this piece of coursework are on the Blackboard site under the ‘Assignments’ section. Consult these before planning your work. Your report must refer to the relevant concepts and literature covered during the MANG1003 teaching and studies through your further reading. The content and classes on teamwork, team roles, motivation, organisational behaviour, and reflection writing will help you with this assessment. It might be helpful for you to individually keep a reflective journal documenting the record of the incidents during your teamwork. You can also take note of your interim reflections to facilitate writing your final report (for example on how you progressed, what happened and why). You should then use the reflective journal to finalise your reflections on your team working experience and to write your critical review report. 2. Writing Your Individual Report a) Include a front title page which should include the module title “MANG1003 Introduction to Management”, the assignment title “Individual reflective report on team working”, the word count, your student ID number, and your team name. Please do not include your and the names of your team members as the assignments will be marked anonymously. b) You should use a ‘true type’ font such as Times New Roman or Arial, font size 12, justified and 1.5 line spacing. Do not use ‘clip art’ pictures and do not use a ‘fancy’ font style, or page borders. c) Structure your report. It is essential to make have a strong and coherent structure and to make the structure obvious, so use numbered headingsto break your report into discrete sections. Adding subtitles (if appropriate) will make the report more structured and easier to read and comprehend. Do this first before you write anything. Your report should have the following sections as a minimum: i. Introduction (i.e., what is the aim of this report) ii. Reflection on teamwork iii. Conclusion (here you should state your three key learnings, clearly labelled, what you have learned and how you might use this knowledge in the future). iv. References d) Start with an outline plan as above, and then start to populate the sections with relevant concepts, examples, and references. Writing is a creative process, and you should expect to write and re-write several drafts. e) Avoid lengthy descriptions and long paragraphs but include more analysis. You should be trying to show us that you can relate the theories and ideas you have learnt about to the incidents of your real teamwork. f) Make sure that the topic is dealt with properly – address all the issues raised and stick to the point. Keep asking yourself “Is this relevant to the issue I am discussing?” If it is not, then do not write it. An important writing skill, which is especially important in management reports, is the ability to get your message across in a succinct and concise manner. In other words, every piece of information in the report should add value to your discussions. Hence, superficial information such as the venue or date of your team meetings should be removed from the text unless you are making a specific point with any of these details. Such details will make your text look like a narrative ‘diary of events’ rather than an academic and analytical report. These will add words without enhancing the analytical value of your report. g) Include a word count at the bottom of your front title page. The word count covers everything in the file (as per the word count function in the software package) including the title page but excluding the Reference list or tables and pictures (if applicable). The word limit is 1500 (+/- 10%). We will stop marking at 1650 words. h) You can refer to others in your group using a pseudonym. For example, you can refer to the actions of by writing a made-up name such as ‘Bob’ and writing ‘(a pseudonym)’ next to it the first time you use it. i) You should include a caption and title for any tables or figures you include, along with a source. You should also include your student ID number and page number on each page (use the ‘page x of y’ format) in a header or footer. j) The Business School requires that you follow the rules on Academic Conduct & Responsibility, and referencing . We will cover these in dedicated classes. Some important things to consider here: References, using the Harvard system, must be given every time you mention a theory, or an author’s or any another person’s idea(s). In other words, any concept and idea you have learned from the academic resources, and you would like to support your discussions with, need to have a citation as to clearly address where you read it. It’s a good idea to try to use the original source if you can (so long as you read the original!). Be selective and only include material that is relevant to your case and use examples to show us that you have really read the references and understood the concepts. Do not be tempted to liberally scatter the names of concepts or references throughout your report as this will be easily picked up by TurnItIn and the marker. Your reference list should only contain references that you have read and used in your text. The reference list (i.e., NOT a bibliography of everything that you have read) should be sorted alphabetically by first author surname: do not separate out different types of sources (books, journals, etc) into different lists. Do not number the list. We will be looking at referencing in more detail in one of the classes and your wider degree programme. Avoid (over-) reliance on websites for your sources as they are rarely peer-reviewed and often contain errors so are not considered as academic references. k) This is an individual report... be sure to have read, understood and followed the guidelines on Academic Conduct & Responsibility that you can find here. l) Reports can easily be marred by poor grammar and spelling. Computer spell-checkers will not always give you the right word e.g., “there” and “their”, “hear” and “here” (or, more amusingly, ‘steakholder’ instead of stakeholder). If you are not sure about a word, use a dictionary. Read your work before you submit. We expect degree-level reports to contain correct spelling and to be grammatically correct. If English is not your first language, there are extra support classes provided to help you with this assignment and further classes are available via the Library and the Student Hub. Use an appropriate writing style. This means avoiding informalities like “haven’t”, “can’t” and “isn’t”, and avoid slang unless you need to use it - in a quotation - to make a point. Do not use abbreviations such as “&” for “and”. Another good rule is to try to keep sentences as short as possible. And please... no text messaging lexis, ‘thnx’. m) Consult the ‘Frequently Asked Questions’ document on Blackboard for further advice and answers to many of your questions. n) There will be specific classes to help you with this in the latter stages of the course, as well as individual time to discuss plans and ideas.
Assignment 6 EMATM0061: Statistical Computing and Empirical Methods, TB1, 2024 Introduction This is the sixth assignment for Statistical Computing and Empirical Methods. This assignment is mainly based on Lectures 15, 16, and 17 (see the Blackboard). You can optionally submit this assignment by 13:00 Monday 4th November. This will help us understand your work but will not count towards your final grade. The submission point can be found under the assignment tab at Blackboards (click the title “Assignment 06” and upload a pdf file). Load packages Some of the questions in this assignment require the tidyverse package. If it hasn’t been installed on your computer, please use “install.packages()” to install them first. To load the tidyverse package: library(tidyverse) 1. The Gaussian distribution Gaussian random variables are an important family of continuous random variables. In this assignment, we will first explore several properties of the Gaussian distribution. Use the help function to look up the following four functions: “dnorm()”, “pnorm()”, “qnorm()” and “rnorm()” . Also, the probability density function of a Gaussian random variable was introduced in Lecture 14. (Q1) Generate a plot which displays the probability density function for three Gaussian random variables X1 ∼ N(μ1, σ1(2)), X2 ∼ N(μ2, σ2(2)), and X3 ∼ N(μ3, σ3(2)) with μ1 = μ2 = μ3 = 1 and σ1(2) = 1, σ2(2) = 2, σ3(2) = 3. Your plot should look like this: (Q2) Generate a plot which displays the cumulative distribution function for three Gaussian random variables X1 ∼ N(μ1, σ1(2)), X2 ∼ N(μ2, σ2(2)), and X3 ∼ N(μ3, σ3(2)) with μ1 = μ2 = μ3 = 1 and σ1(2) = 1, σ2(2) = 2, σ3(2) = 3. (Q3) Generate a plot for the quantile function for the same three Gaussian distributions as above. Describe the relationship between the quantile function and the cumulative distribution function. (Q4) Now use “rnorm()” to generate a random independent and identically distributed sequence z1, ⋯ ,zn ∼ N(0,1) so that each zi ∼ N(0,1) has standard Gaussian distribution. Set n = 100. Make sure your code is reproducible by using the “set.seed()” function. Store your random sample in a vector called ““standardGaussianSample”” . (Q5) Suppose z ∼ N(0,1) is a Gaussian random variable. Take α, β ∈ ℝ and let W: Ω → ℝ be the random variable given by W = αz + β . Then W is also a Gaussian random variable. We will use this fact to create samples of Gaussian random variables from samples of standard Gaussian random variables. Use your existing sample stored in “standardGaussianSample” to generate a new sample of the form y1, ⋯ , yn ∼ N(1,3) with expectation μ = 1 and population variance σ 2 = 3. The i-th observation in this sample should be of the form yi = α ⋅ zi + β, for appropriately chosen α, β ∈ ℝ, where zi is the i-th observation in the sample “standardGaussianSample”. Store the generated sample of y1, ⋯ , yn in a vector called “mean1Var3GaussianSampleA” . So to answer this question you need to decide the value of α and β, such that yi has the required expectation and variance. (Q6) Reset the random seed to the same value as the one you used in (Q4) using the “set.seed()” function and generate an i.i.d. sample of the form y1, ⋯ , yn ∼ N(1,3) using the “rnorm()” function (instead of using “standardGaussianSample”). Store this sample in a vector called “mean1Var3GaussianSampleB” . Are the entries of the vectors “mean1Var3GaussianSampleA” and “mean1Var3GaussianSampleB” the same? (Q7) Now generate a graph which includes both a for your sample “mean1Var3GaussianSampleA” and a plot of the population density (the probability density function) generated using “dnorm()” . You can also include two vertical lines which display respectively the population mean and the sample mean. Some guidance for creating the plot: It would be helpful to look at the example provided in Section 3.3(Q4) of Assignment 5. You may want to use the “geom_density()” and “geom_vline()” functions. In particular, both “geom_density()” and “geom_line()” have an argument called “data” that you may want to explore. Also, you can specify your own color by using the “scale_color_manual” and your own line type by “scale_linetype_manual” . Your plot should look similar to the following: (Q8) (*) This is an optional question (*). If you are short on time you can work on the other questions first. Recall that for a random variable X: Ω → ℝ is said to be Gaussian with expectation μ and variance σ 2 (i.e., X ∼ N(μ, σ 2)) if for any a, b ∈ ℝ, we have Suppose Z ~ N(0,1) is a Gaussian random variable. Take α, β ∈ R and let W: Ω → R be the random variable given by W = αZ + β. In (Q5) we have assumed that W constructed in this way is a Gaussian random variable. Now, apply a change of variables to show that W is a Gaussian random variable with expectation β and variance α 2. Hint: can you derive the expression of ℙ(c ≤ W ≤ d)? 2. Location estimators with Gaussian data In this question we compare two estimators for the population mean μ0 in a Gaussian setting in which we have independent and identically distributed data X1, ⋯ ,Xn ∼ N(μ0, σ0(2)). The following code generates a data frame consisting of the mean squared error of the sample median as an estimator of μ0. set.seed(0) num_trials_per_sample_size 0, Please note that in the Hoeffding Theorem we additionally assume x to be bounded. We can view Hoeffding’s inequality as a variant of the law of large numbers. However, Hoeffding’s inequality gives us information about the rate of convergence. In particular, the sample average for bounded random variables converges exponentially fast to its expectation. Hoeffding’s inequality is a precursor to Vapnik-Chervonekis theory which serves as a foundation for the theory of Statistical Machine Learning.
COMM 392 - GROUP PROJECT: PREDICTIVE ANALYTICS AND SUPERVISED MACHINE LEARNING 1. Project Overview and Deliverables The group project activities contribute 40% of each student’s final mark in the course (35% for the project analysis and report and 5% for the predictive analytics competition, which counts in the participation grade). Winning the competition improves the final grade by 3% (first place), 2% (second place), and 1% (third place). Your task in this project is to work with your team of 4-5 students to solve a business problem based on a given dataset for an organization. The business context, dataset, and detailed project tasks are described in the next sections. For five days of competition (leading up to the project submission deadline), the teams have the opportunity to compete by developing increasingly accurate predictive models. Submitting a new model on each day of the competition is worth 1%. The best predictive model will be determined based on the F2 score of the champion model at the testing stage. To participate on a given day, a team must upload an improved version of their KNIME workflow to the appropriate assignment folder before midnight. The results of each competition day are revealed in the next day by the instructor. You will also submit a Project Report that summarizes your work on the following Project Steps, which follow the CRISP-DM process: 1. Business Understanding 2. Data Understanding and Preparation 3. Predictive Modeling/Classification a. Classification using Logistic Regression b. Classification using Decision Tree c. Classification using Ensemble methods: Gradient Boosting & Random Forest d. Compare the results of the different techniques and evaluate the performance of the selected champion model 4. Post-prediction Analysis: Score the model on a new dataset and evaluate its prediction performance 5. Conclusions and Recommendations All the analytics steps must be conducted in KNIME. The project steps are further explained in the sections below. Here are the deliverables for this project: Deliverable Submission Mode Deadline Competition Submissions Make a daily submission over a period of 5 days. The KNIME file uploaded must contain the latest predictive workflow of the team, and the F2 score of the champion model at the testing stage. Make sure to always properly embed the data file into the workflow as practiced in class. The KNIME files with the workflow for each day should be renamed “Group Project_Day X_Team XX”. It should include the workflow you will develop to train, validate, test, and score the algorithms. .knar /.knwf files uploaded to the appropriate assignment folders on course website The last 5 days leading up to the project submission deadline (one submission each day) Project Report The report should include the sections outlined below. Your report should clearly describe what you did, any assumptions you made, the results you obtained, what you learned, and any gleaned insights as appropriate. Use the provided report template. 1. Executive Summary 2. Business Understanding 3. Data Understanding and Preparation 4. Predictive Modelling/ Classification 5. Post-prediction Analysis 6. Conclusion and Recommendations 7. Appendix: Tables, Figures, Screenshots of KNIME output, and any other information that supports your analysis MS Word file (DOC, DOCX) uploaded to the appropriate assignment folder on course website See syllabus Overview of ML process for group project The KNIME file with the final workflow should be renamed “Group Project_Final_Team XX”. It should include the full workflow you will develop to train, validate, test, and score the algorithms. Make sure to always properly embed the data file into the workflow as practiced in class. .knar /.knwf file uploaded to the assignment folder on the course website KPI Spreadsheet Excel file (XLSX) uploaded to the Submit the KPI spreadsheet used to evaluate the financial impact of your AI solution. assignment folder on course website 2. Background You and your team form. the advanced analytics department of a U.S. nationwide property and casualty insurance company. Your team specializes in analyzing the insurance fraud occurring in auto accident claims. According to a 2012 Insurance Research Council (IRC) study, Insurance Fraud accounted for up to 17% of total claims payments and up to $7.7 billion was fraudulently added to paid claims for auto insurance bodily injury payments. And this doesn’t include all the forms of auto insurance fraud. Your company’s senior management is well aware of these fraud statistics and your company can cite similar statistics from its own data; a 2017 internal study found a 20% fraud rate exists! Meanwhile, senior management has also been watching the Property and Casualty (P&C) industry become disrupted by new players, and they've examined the reasons behind its own slowly weakening market position. In response, they are now seeking to reinvent the firm by leveraging AI in away similar to Lemonade Insurance. While the expected benefits include a reduction in costs by reserving fraud investigation resources (i.e., human workers manually investigating the claims) only for those most suspicious claims, management sees other benefits to modernization, such as being able to market the company to new segments of the population. For example, the company’s latest data showed that the current customer’s average age is about 44. Management wishes to target younger adults who demand fast claims payouts, service by smartphone, and lower premiums. This modernization partly hinges on management’s objective that a real-time, AI-enabled predictive model is (i) trustable and (ii) demonstrable to be better than the current state “legacy” process as measured by an anticipated positive change in a specific key performance indicator (KPI) (more on this below). Management wants to know that the idea is viable in these two ways. To this end, management has asked your team to build an AI proof of concept (POC) that reduces the net costs of fraud by increasing the efficiency in being able to catch fraud when it happens. In sum, your AI solution aims at automatically identifying potentially fraudulent claims that will then be investigated by human experts. 2.1. Trustable Results To demonstrate trust in the results of the AIPOC, management has requested evidence that the data flagged as fraudulent will likely contain at least 25% more cases that are actually fraudulent than a random sample of the same data. As shown later, you can use the Lift table and graph in KNIME to implement this constraint. 2.2. Key Performance Indicator (KPI) The ultimate KPI of interest to senior management is “Net Fraud Savings.” This KPI is calculated as the dollar value of suspected fraudulent claims that are flagged for investigation and found to be truly fraudulent MINUS the Total Cost of fraud investigations. The Total Cost of Investigations (TCI) = Number of Investigations (NI) * Cost per Investigation (CPI) For simplicity, the Cost per Investigation (CPI) of claims has been reduced to a simple formula: • $1,000 per claim investigated for the first 600 claims • $2,500 per claim investigated for every claim after the first 600 claims investigated. The business case for a predictive AI model is illustrated by a simple calculation used in the Figures below. An AI model that does nothing except correctly identify fraud better than chance (20%, which is the proportion of fraudulent cases in the dataset) increases the KPI. See below how that one KPI can help tell the story! An optimal point exists for this KPI, and it is a function of the model’s predictive capability and the number of investigated claims. For example, if your AI model were able to predict fraud and it correctly identified 75% of the fraud cases (i.e., 75% success rate), you could then calculate the “money not paid out on fraudulent claims” for a given number of these suspected fraudulent claims you decide to investigate. This is because, in the primary dataset, each claim has an estimated claim payment value (in the “claim_est_payout” column). Deducting the total cost of fraud investigations from this amount will give you the KPI metric of “net fraud savings” . In the KPI Spreadsheet provided (auto_claims_kpi.xlsx), you can try these calculations yourself. In the first worksheet (“KPI Calculation”), simply enter a success rate in the "% successfully identified" column (cells B6:B11) in the top table (don’t touch the bottom table at this point), and then observe how the KPI of “net fraud savings” increases and decreases based on the inputted success rate as well as the number of investigated claims. In the Figures below, you can see the KPI values for three scenarios: 20% success rate (the legacy model, or current state), a model based on 75% success rate, and a model based on 45% success rate. Note: These scenarios only serve to demonstrate the value of a hypothetical AI model to management. After you obtain your KNIME results, you will need to use the bottom table of the KPI spreadsheet with the actual results from your analysis so that you can calculate an optimal KPI. More on this in the Post-prediction Analysis section. Figure 1: KPI Based on Current State (20%) Figure 2: KPI - Future State Using 75% Success Rate for Illustration Figure 3: KPI - Future State Using 45% Success Rate for Illustration 3. Project Files and Data Sets In addition to this document (the project description), the following files and data sets are included with the project. 3.1. Project Report Files and The Primary Data Set For the project report, the following files are included: The Primary Data Set Management had previously commissioned the investigations department to do a deep dive into fraudulent cases of auto claims. This resulted in a thorough internal study on fraud where 30,000 records of auto insurance claims were classified as fraudulent or non-fraudulent. Having this ground truth was essential to management's objective of reducing fraud costs. That study also confirmed management's expectation that 20% of cases were fraudulent and 80% were non- fraudulent. This is the dataset you will use for your AI POC. Senior management has split the primary data set containing 30,000 records and provided you with two files: (1) a file named auto_claims.csv, which contains 20,000 records to be used for developing (training, validating, and testing) your AI proof-of-concept, and (2) afile named auto_claims_score.csv, which contains the remaining stratified subset of 10,000 records as a scoring data set. That scoring data set will be used later for scoring your champion AI model. The scoring data set will also be the basis for calculating the optimal KPI in the KPI spreadsheet provided to you. You will use the auto_claims.csv file to train and compare your supervised learning AI models. First, you will need to decide how to split the data so that you end up with three subsets: 1. Training Subset: The training subset will be used to develop your AI models. Your team will create several models using different classification algorithms that you learned in the course (logistic regression, decision tree, gradient boosting, and random forest). 2. Validation Subset: The validation subset will be used to validate your AI models. Using this subset,you will obtain the relevant performance measure for each algorithm (the F-2 score, as explained later), compare the models against one another, and select a champion model. 3. Test Subset: The test subset measures the performance of your champion model. Werecommend starting your iterative ML journey with a split of 60%-30%-10%, but you may choose to tryout other ratios (or even use the “cross-validation” technique) to see whether your trained results improve. The data file you are given contains information on more than 20 attributes that could be used to predict fraudulent auto claims. The final column in the file, “fraud”, represents the class target, which indicates whether a claim was fraudulent or not. It can be presumed to be ground truth. Here is the data dictionary for the data file: Table 1: Data Dictionary - Auto Insurance Claims The second data file you receive from management, auto_claims_score.csv, represents the scoring data set that will be used for scoring the champion AI model. It has all the data EXCEPT that the class variable has been removed. Thus, it cannot be used for training or developing models. Remember that this scoring dataset should only be used later on in the project, for scoring.
BUSOBA 2321 – Group Exercise 2024 Autumn Semester Due Monday, December 2nd at 11:59pm · File Name (1%) – Save your solution as “BusOBA 2321 – Group XXX” – inserting your 3-digit group number for the “XXX” · Cover Page (4%) – add all team members names and dot numbers as indicated. o List names in alphabetical order by last name o No more than 4 members to a group; your assigned group is available on Carmen. o If a member does not contribute, do not include their name on the cover sheet. o If a team member is unresponsive or inaccessible through Monday, November 18th, let your instructor know and that person will be dropped from your group. o Individual submissions will be accepted but will incur a 20% deduction from the grade earned, unless otherwise discussed with your professor. · There are 5 problems: a decision-making problem, a decision tree, an optimization and sensitivity analysis, a network model, and a simulation. · Submit the worksheet via Carmen. o 1 submission per group using the provided template. · Your submission includes 11 total worksheets: o Cover sheet – 1 sheet o Decision making - 1 sheet o Decision tree – 2 sheets § “Problem 2 Tree” requires no work but must be included. o Optimization/Sensitivity – 4 sheets § “Problem 3 Table” requires no work but must be included. o Transshipment – 1 sheet o Simulation – 2 sheets · Up to 20% will be deducted for “non-professional” reports – neatness and formatting count. · Incomplete assignments will receive a grade of zero. · Should the grader feel a poor effort was made the entire assignment will receive a zero. · If the assignment is submitted late all members will receive a reduction of 33% per day. · Solver MUST be complete (i.e., executable) for problem 3 and 4 in your final submission or you will receive a ZERO for each problem that is missing the solver details! If group members used Excel Online to share the excel workbook with group members or if a problem was copied from another workbook, the solver program may not transfer with the copied/shared files. Each group is responsible for checking its final submission to ensure that solver is properly filled out for each problem. Should solver be missing or not run for a problem the group will receive a zero for the problem. It is advised to complete the group exercise in Teams rather than trying to combine various files. · Some advice for completing the Group Exercise o The Group Exercise is designed to be COMPREHENSIVE – to include almost everything covered in the course. o The Group Exercise is designed to IMPROVE YOUR ABILITY TO USE THE COURSE MATERIAL, to solve problems, to apply simple logic and algebraic principles in the solution of business issues. o The Group Exercise provides all the information you require to solve the problem, but not always in a straightforward array of data – you may have to THINK THROUGH THE PROBLEM. o The Group Exercise includes somewhat complex problems which are designed to be completed through DISCUSSION AND COLLABORATION. o The Group Exercise is designed to PREPARE YOU FOR THE FINAL EXAM. o The Group Exercise is not designed as a DIVIDE AND CONQUER assignment – assigning individual group members to an individual problem, then assembling these individual efforts into a finished project will not be in any group member’s best interest. · Work together, work early. You will be given chances to work with your group during lecture and recitation, where instructors and TAs are available to help you. During these sessions, and during office hours, we will easily recognize those who have not put any work or thought into the assignment and we will defer helping you until we feel you have put work and thought into the project. · And, in case you missed our earlier subtle hints: Question 1 Decision Analysis An automotive company, KSMG, plans to launch a new car model, Toyota Ralph4 in five trims—each designed to cater to different customer segments. Due to global supply chain disruptions and raw material shortages, Havi and Tessa must decide which trim to focus production on for the next five years to maximize profitability and manage risks. Each trim varies in production cost, customer demand, and supply chain dependence. Additionally, the company’s production capacity is limited to only one trim level for the next years, as retooling for multiple trims would exceed budget and disrupt timelines. The company is also affected by raw material costs ( lithium prices) and government incentives for electric vehicles (EVs). Your team must consider market conditions, production constraints, and demand fluctuations to recommend which trim to manufacture. Market Conditions and Constraints: Market analysts have provided four potential market scenarios, each influenced by factors such as consumer behavior, material costs, and government incentives. · Material Costs: o Lithium prices rise with increasing EV adoption and resource scarcity. o IF the Lithium prices are moderate, it will cost $500/kg o IF the Lithium prices are high, it will cost $1200/kg o IF the Lithium prices are very high, it will cost $1600/kg · Government Policy: o EVs receive a $10,000 subsidy per unit, making them more competitive in certain markets. Market Scenarios: Scenario/conditions Economic Downturn Steady Recovery Green Revolution Raw Material Crisis Lithium Prices Moderate Moderate High Very High Government Subsidy No No Yes No Demand Shift Strong preference for Base and Mid-tier Balanced demand across all trims High demand for EVs and Premium trims Limited capacity for EVs, focus on Base Trim Demand per Market Scenario: Scenario/car trim Economic Downturn Steady Recovery Green Revolution Raw Material Crisis Base Model 8000 6000 3000 9500 Mid-Tier 5000 5000 3500 6000 Premium 2000 3000 4500 1000 Luxury 500 1500 2000 200 Electric (EV) 300 1500 3000 100 Trim/Cost Production Cost per Unit MSRP (Selling Price) Annual Production Capacity Lithium Usage per Car in kg Base Model $20,000 $25,000 9000 0 Mid-Tier $28,000 $35,000 5000 1 Premium $40,000 $50,000 4000 1.5 Luxury $55,000 $70,000 1600 2 Electric (EV) $60,000 $80,000 3000 3 Trim Cost/profit Problem 2 – Decision Tree – KSMG Automotives Executive Meeting (15%) After such a strong performance in the case competition, the executive team of Klinker Automotive Group receives a letter in the mail inviting them to the National Automotive Conference in Washington, DC. With winter break travel planning on the rise, the team needs to act fast to get their flights booked before prices soar through the roof. The team wants to know what flight to take and how much the trip will cost based on the decision. Ryan has derived the probabilities and payoffs for each option, with the payoffs being calculated using “Units of fun” or Utils for short. He has also created a decision tree to use when determining the best course of action for the executive team. As a last resort, the team can also pack up the trusty company van “Havi McQueen” early in the morning and drive the 6 hours to DC. Below is a list of the six best flights that Ryan was able to find to get the team to Washington DC. Of the six choices, three of them require you to take a connecting flight (Delta, American, and Spirit), two options allow you to take a non-stop flight (Southwest and United), and one will allow you to skip the hassle altogether. (Driving). Each member of the executive team has ranked all of the available options based on routing, price, and time with 1 being the least preferred and 6 being the most preferred. The rankings are shown below in Table 2. Table 1: Flight Results Table 2: Util Rankings The calculation of your initial utils will be based on the total number of votes for each flight, whether or not there are thunderstorms, if your flight gets delayed, or if the airline loses your bags. While both non-stop flights leave early in the morning and get the team to DC well before their meeting, on their way to the airport, Jeslyn sees the skies are much darker than usual. Ryan checks the weather and sees that there could be some strong thunderstorms rolling through Columbus early in the morning, so the team must plan accordingly. For non-stop flights: ● If there are thunderstorms and your flight gets delayed for more than 2 hours, you will get 20% of the total votes for that choice. ● If something else delays your flight for more than 2 hours then you will get 45% of the total votes. ● If there are thunderstorms, but your flight arrives on time you will get 60% of the total votes for that choice. ○ If the weather is great and your flight leaves on time, you will receive the full utils for that option. While all of the connecting flights will avoid the early-morning storms, the team must check their bags in order to fit on the flight. However, the team can carry-on their bags for a fee of $60.00 per bag. This unexpected fee takes a hit on the team’s excitement and reduces the total utils for that airline by an additional 18%. For connecting flights: ● If the airline loses your bag AND your connecting flight is delayed, you will get 11% of the total votes for that choice. ● If the airline loses your bag, you will receive 35% of the total votes for that choice. ● If your connecting flight is delayed your total utils will be reduced by 40% ● If you get lost while driving, you will receive 8% of the total votes for that choice. The probability of delays, weather, losing your bags, and getting lost are listed below: Problem 3 – Optimization and Sensitivity Analysis – KSMG Automotive (30%) Using the information provided, create a linear program using solver in the ‘Problem 3 - Part 1’ sheet in the provided Excel workbook. Then create a sensitivity analysis using that optimization model to answer the questions on the problem 3 – part 3 answers sheet. Part 1 – Construct an optimization model using the information and the table provided on the next page KSMG automotive is a new car dealership located in Columbus, Ohio. They want to purchase an assortment of cars to sell for the upcoming year. They will purchase a mix of SUVs, pickups, sedans, crossovers, and motorcycles. The dealership can pick the number of each make and model. You and your team are responsible for purchases the best arrangement of cars to meet the demands of the Columbus market and consumer preferences while maximizing the dealership’s monthly profit. The CEO has briefed your team on what features are available to be purchased and the constraints facing KSMG automotive. While the CEO briefed you on the constraints, your team took the following notes: · The vendor currently has 75 factory workers, who each work 40 hours per week, 4 weeks a month to add on the additional features. · Some of the vehicles have four-wheel drive which is sold to customers for an extra $3000 on top of the car’s sales price. · The base cost for the vehicles varies depending on the type of vehicle. Costs are listed below: o SUV: $18,000 o Sedan: $9,000 o Pickup: $22,000 o Crossover: $15,000 o Motorcycle: $3,000 · At least 30 SUVs must be purchased, 15 Pickups, 25 Sedans, 10 Crossovers and at least 5 but no more than 20 Motorcycles. · There must be exactly 130 Vehicles purchased in total for the dealership this upcoming year. · As market demands are changing in preference towards electric and hybrid cars at least 40%, but no more than 65% of cars must be electric or hybrid. · 55 customers requested a high performing car for better off-road performance and require that the vehicles have 4WD and at least 300hp · With gas prices on the rise: o Avid road-trippers want at least 42% of all SUV’s and crossovers to have at least 35MPG highway o People who commute to work in the city want at least 27% of all Sedans and Pickups to have 30MPG city. · Due to budget constraints, the manufacturing company is given $93,000 per week to install premium interior features which must be evenly split between features. (leather seats, heated/cooled seats, pre-set seats, Weather mats, carplay, and premium sound). · KSMG wants to purchase an equal amount of 100hp and 200hp motorcycles. · At least 70% of SUVs and crossovers must have supercruise for long trips. The table provided shows various statistics about each vehicle KSMG is interested in purchasing to sell the next year, with each ‘X’ indicating the features that is included in the vehicle. NOTE: Normally a problem like this would include an integer constraint as its not possible to purchase a partial car. However, you can not generate a solver sensitivty report with an integer constraint, so do not include one in your problem! Part 2 – Using the optimization model from part 1, run a sensitivity analysis using solver, rename the sensitivity report to ‘Problem 3 – Part 2’ Part 3 – Using the sensitivity report from part 2, answer the questions on the ‘Problem 3 – Part 3’ sheet
