Select a decision problem that is of interest to you and is manageable. For this project, you can use a real-world
decision problem, but not necessarily real-world data. It is perfectly okay to use simulated data, as long as it is a
good representation of the real decision problem.Once you have carefully investigated your decision problem, you will build a small decision support model to
help the decision-maker facing this problem. You are welcome to use any tool you prefer, such as spreadsheets,
databases, Tableau, Solver, R, Rattle, etc.
The model can be used for the following:
It can perform different types of quantitative analysis
It can perform data visualization which can aid the decision-maker
It can help the decision-maker to test out different solution alternatives[— 20: Ju: Creditscoraisx Fille CrodiSooreCV.cev, CraditSooreTastosy Credit Scores (regression tree). A consumer advocacy agency, Equitable Ernest, is interested in providing a service that allows an individual to estimate his or her own credit score (a continuous ‘measure used by banks, insurance companies, and other businesses when granting loans, quoting premiums, and issuing credit). Data from several individuals has been collected. The variables in these data are listed in the following table. Variable Description Bureaulnquiries number of inguiries about an individual's credit CreditUsage percent of an individual's credit used Totalredit total amount of credit available to individual CollectedReports number of times an unpaid bill was reported to collector agency Missedpayments number of missed payments Homeowner 1 if individual is homeowner. 0 if not CreditAge average age of individual's credit TimeonJob. how long the individual has been continuously employed Creditscore score betyieen 300 and 850 with larger number represer increased credit worthiness Predict the individuals’ credit scores using an individual regression tree. Use CreditScore as the target (or response) variable and all the other relevant variables as input variables. a. In the construction parameters of the tree, set the minimum number of records in a terminal node to be 244. What is the RMSE of the best-pruned tree on the validation data (a static validation set or through a 10-fold cross-validation procedure) and on the test set? Discuss the implication of these calculations. b. Consider an individual with 5 credit bureau inquiries, has used 109 of her available credit, has $14,500 of total available credit, has no collection reports or missed payments, is a homeowner, has an average credit age of 6.5 years, and has worked continuously for the past 5 years. Using the best-pruned tree from part (a), what is the predicted credit score for this individual? > c. Repeat the construction of an individual regression tree, but now set the minimum number of records in a terminal node to be 1. How does the RMSE of the best-pruned tree on the test set compare to the analogous measure from part (a)? In terms of number of decision nodes, how does the size of the best-pruned tree compare to the size of the best-pruned tree from part (a)? ” S0aTAfie Credit Scores (random forest estimation). Refer to the scenario in Problem 20 regarding the estimation of individuals’ credit scores. Apply a random forest of regression trees using CreditScore as the target (or response) variable and all the other variables as input variables. a. Experiment with the number of trees and the number of variables per tree to recommend a random forest model (based on predictive performance on a static validation set or a cross- validation procedure). b. Which variable is most important in the random forest model? SOM 485 - Decision Support Systems Class Project Select a decision problem that is of interest to you and is manageable. For this project, you can use a real-world decision problem, but not necessarily real-world data. It is perfectly okay to use simulated data, as long as it is a good representation of the real decision problem. Once you have carefully investigated your decision problem, you will build a small decision support model to help the decision-maker facing this problem. You are welcome to use any tool you prefer, such as spreadsheets, databases, Tableau, Solver, R, Rattle, etc. The model can be used for the following: · It can perform different types of quantitative analysis · It can perform data visualization which can aid the decision-maker · It can help the decision-maker to test out different solution alternatives. Deliverables: 1. A written report containing the problem definition, decision support model and results. 2. Optional presentation in class preferably using PowerPoint. 3. Optional demo of the application during the presentation. If your team is unable to come up with any new idea for your project, you may consider the Suggested Case Problems file and try to add more features: Grading Criteria Project Report: Submit a report that must be typed and may include the following: 1. Introduction 2. Define the problem and issue(s) 3. Approach and tool(s) used for the analysis 4. Features or results which include charts (not the spreadsheet) and brief analysis of each 5. Conclusion 6. Appendix (include URLs for Tableau Public and data file source) 7. Input and output files or model spreadsheet should be submitted separately Optional Presentation and demo (extra 3 points max): 1. No more than 6 minutes 2. Define the problem and issues 3. Present the model or dashboard to class on Zoom 4. Features and/or results 5. Q & A Note: There will be one grade for both written report and presentation Grading Rubric for Written Report and Presentation 1. Creativity (20%) 2. Technical Content (30%) · Technical correctness · Appropriate level of details and thoroughness of documentation 3. Layout/Visuals (20%) · Consistent presentation of graphics · Appropriate and supports the objectives 4. Organization & Presentation (30%) · Clearly identified purpose and approach · Content is clearly organized and supports the objective · All paragraphs are well-organized; use of sections is logical and allows easy navigation through the document · Formatting of the document is professional and includes a professional cover page · Easy to read and grammatically correct · Provides explanations on data selection and credible sources with clear and complete references · All sources are correctly and thoroughly documented; appropriate citation forms · All figures, tables and equations are clearly and logically identified and support the text · Uniform document design and layout · All graphical documents, sketches, maps, etc. are creative, professional and support the text Page 2 of 2 Sheet1 Case ProblemTextbookpageProblem # /Case #Chapter 7DataToolsNotes FoodmartI18039-424FoodmartExcel, Tableau, RProvide useful statistics, data visualization, dashboard PrecipitationI181454srn_pcp.txt, srn_data.txtExcel, Tableau, R Tim’s Retirement PlanningII4027AlumniGivingExcel, Tableau, R Consumer Research, Inc.II4047ConsumerExcel, Tableau, R Predicting Winnings For NASCAR DriversII4057NASCARExcel, Tableau, R Retirement PlanII544Case10Excel, Tableau, R Academy Awards (Logistic Regression)II503239OscarsTrain.csv, OscarsValidation.csvRattle, R, Excel, Tableau Housing Price BubbleII503249PreCrisisCV.csv, PostCrisisCV.csv, OnMarketTest.csvRattle, R, Excel, Tableau Association Rules of Grocery Store TransactionsII250215GroceryStoreList.csv, GroceryStore Stacked.csvRattle, R, Excel, Tableau SOM485 Spring/Fall 2020 Class Project Examples: 1. NBA Shot Selection: Analysis 2. Protection Services 3. How Much Will My House Sell For? 4. Relation of Three-Point Shots and Wins 5. 3 Point Shots vs. Number of Wins in the NBA 6. A transportation model for masks 7. Future Electric Vehicle Incentives 8. U.S. Crime Rate Analysis 9. Mid city’s single-family house 10. Compare three different neighborhoods to invest in real estate 11. COVID-19 Resource Distribution Support System 12. COVID-19 and Unemployment 13. COVID-19 and the effective of mask