MIS Excel Data Analytics Capstone Project
Overview
This project requires that you use the theory and tools learned throughout this of the course:
- Big Data
- Business Intelligence and the Decision-Making Model
- Customer Relationship Management Systems
- Defining Data Problems
- Data Modeling
- Data Cleansing
- Data Mining with Classification and Prediction
- Mining analysis using error and lift-chart reports
- Data Forecasting
Identify a Business Problem for Prediction and Classification Mining
Using the Stanley A Milner Library data referenced in the assignments, analyze the data available to define one real-world Classification and one prediction business problem to solve. Here are some examples:
- Can library cardholders be categorized from a combination of variables such as income, home ownership, employment status, etc.?
- Can we predict the frequency of visits to the Stanley A Milner Library from a combination of variables? If, so what were the variables and how can they be used to improve the efficient use of library resources?
- Can we predict the primary mode of transportation based on a combination of library variables? If so, we can collaborate with Edmonton Transit Services and share data to improve popular bus routes to the downtown library.
- Can we correctly determine if library visitors own a home? If so, we can have a more efficient marketing campaign to homeowners.
- Can we correctly determine if library visitors are newcomers to Canada? If so, the library can leverage the information to create learning programs for the target demographic.
As illustrated by the bolded words in each problem statement, there will be one specific output for each business problem.
Please have a look at the red “Legend” tab in the library worksheet to see all available variables.
Include the business problem statements in the Appendix section of the report.
Creating a Prediction and Classification Model and Technical Report (Appendix Content)
As you are going through this process you must document what changes you make to the model data with each iteration and the decisions behind the changes and why you are making those decisions. The process of developing your model is the most important part of this process, so ensure you are making improvements and documenting the reasoning and impact (screenshots and point form). Generally, this will involve reducing the number of inputs (some columns less relevant to the problem) and checking to see if the error reports and lift charts have improved. Note that the columns do not need to be deleted from the spreadsheet/partition to execute another run. Instead, remove the parameter from the Data Options.
Include the business problem in the Appendix section of the report.
For example, after obtaining the first set of error reports and lift charts of homeownership from the full set of data, the configuration below will disregard the consideration of whether a person is an employee of the City of Edmonton on the next trial:
Complete a total of 6 data mining trials (including the initial run with all data) for your defined Classification and Prediction business problem (6 for each problem 12 in total). Change/Remove variables between each run and switch between Tree and k-Nearest Neighbor.
Minimum Guidelines for Running the Simulations:
- Run 3 Tree and 3 k-Nearest Neighbor mining simulations for each business problem to get a variety of results to analyze.
- You may use the following methods for your Tree mining runs in any combination:
- Broad Mining Method: Exclude 3-4 variables in a single run (excluding Record ID). Use this if you are unsure of which variables having influence of the output.
- Narrow Mining Method: Include 4-5 variables in a single run (ensure tree levels is set to 4-5). Use this method if you have an idea of what variables influence the output. Specify why the input variables are selected in the technical report.
- For the tree parameters, change the levels setting from 10 (from assignment 2) to 5-7 for better results.
- For k-Nearest Neighbor, you can use a k-value between 5-7.
Note that it is entirely possible that a new trend may be discovered solving an entirely different business problem. Recall that discovering new trends is a key concept of Business Intelligence. If such a trend is found, document the new discovery in the report and determine if it is valuable information that can be added to the business recommendation in the next section.
Prediction data mining may not lead to a sufficient R2 value (>0.3). If all 3 runs have low R2 scores, keep the result and discuss in the business report on how the organization should use this knowledge. For example, if the current data set does not give a good prediction on the type of transportation used, a CRM system can be setup to collect the data for future use. Do explain the business value of the venture.
Write a Business Recommendation based on the Mining Results
As IT business consultants, write a recommendation to the Edmonton Public Library on how they should use the mining results to improve their business. Be sure to indicate the level of confidence using the error reports and lift charts from the best classification and prediction runs. You may have a single recommendation, combining both classification and prediction problems, or have two separate recommendations addressing each classification and prediction problems separately.
For example, if our model is accurate with categorizing volunteers from a combination of variables, how can the Library make use of the information to conduct better business?
Other business application examples can be found in the Rainer Textbook for reference. The chapter slides are a good reference for ideas regarding potential topics to discuss:
- Chapter 5, Pages 127-130 (Big Data)
- Chapter 11, Customer Relationship Management and Supply Chain Management
- Chapter 12, Business Intelligence and Analytics
- Chapter 12, Pages 338-341 (Data Mining)
The format of the business recommendation should adhere to the following guidelines:
- 12pt Arial font, 1.5 spacing.
- Sections of the document:
- Cover Page
- 1 Page Executive Summary
- 5-6 Pages outlining the business opportunity/opportunities with the trends discovered. Only include content from the best classification and prediction models and how it supports your recommendation. Do not have more than 1 page discussing the data in this section.
- Conclusion
- Appendix with the technical report
- Screenshots of Error Tables and Charts
- Highlighting the best prediction and classification models
- How the best prediction and classification models were determined. (point form acceptable only in this section)
Grading
Deliverables
The deliverables for this project are:
- A paper that containing
- Your recommendation for each of the business problems based on the best classification and prediction models.
- Appendix
- A classification business problem
- A prediction business problem
- The technical results of your modeling exercise including
- the initial run
- each trial trail run with a report on the changes between each trial run
- Identifying which model is the best (include screenshots of comparison error reports and lift charts)
- Your spreadsheet with the data mining results.
Rubric
| Item | Weighting | Notes |
| Classification Business Problem Statement | 5% | |
| Prediction Business Problem Statement | 5% | |
| Spreadsheet Construction | 5% | |
| Predictive Mining and Trials | 10% | |
| Classification Mining and Trials | 10% | |
| Report | 50% | |
| Technical Explanation of Process (in appendix) | 20% | |
| Recommendation based on findings (main paper) | 30% | |
| Overall Quality of Presentation | 15% | Cover page, table of contents, appendix, logical presentation of information |
The post MIS Excel Data Analytics Capstone Project appeared first on My Assignment Online.