Reference no: EM132358783 , Length: 7 Pages
Assignment - Descriptive Data Analytics: A Review
For the assignment, you will use the Data Analytics spreadsheet. There are two parts to this assignment.
Time for some exploring: You are a data analyst tasked to provide analysis of the data provided by the data warehouse team. You decide to use two unsupervised methods: clustering ( k-means) and association analysis (market basket analysis). This analysis will help the marketing team to group each widget into three or four different levels of products at different pricing. The market basket analysis will help operations and sales teams understand which products tend to be purchased together for potential opportunities to maximize shelf space or up-sell during the time of purchase.
Part 1 (k-means) of the assignment: Use the k-means algorithm with either Microsoft Excel or SAS on the data contained on the worksheet titled "K." Suppose the centers of each cluster are C, F, I, and L. Run the k-means algorithm for one epoch. What was the outcome of your experiment? Describe the clusters created with the experiment? What belongs to which cluster and what are the centers of the new clusters themselves?
Part 2 (basket analysis) of the assignment: You will work with the worksheet titled "Basket." Run experiments using with either Microsoft Excel or SAS, and run an association algorithm to obtain a number of combinations (itemsets) based off the data within the worksheet. Perform your analysis on the output of your association algorithm. What are the most common itemsets? What is the number of items within the top five itemsets? What is the average value of the top five itemsets? What is the total value of the tickets that contain items in the top five itemsets? What can a business analyst do with this information? Why is this information interesting? Is this information useful to solving a business problem?
Write a paper (5-7 pages for the body section). Use APA (6th edition) style and format; include your analysis and answers to the exercises in parts 1 and 2 above, with a minimum of five references; and cover the following topics:
1. Explain how and why developing and running experiments using cluster and association algorithms can help organizations solve business problems and improve data and information accuracy.
2. Explain why you selected and used the analytical software tool for your experiments and how the tool is useful for data analytics.
3. Demonstrate how analytical and statistical methods, processes, and tools are used to help decision makers make better decisions.
4. Demonstrate how analytical and statistical tools are used to aggregate data into information and knowledge with analysis and experimentation.
Assignment Requirements - Written communication is free of errors that detract from the overall message. Resources and citations are formatted according to APA (6th edition) style and formatting. Total 5-7 pages, excluding the references page.
Note - This assignment analysis can be done in either excel or SAS.
Attachment:- Descriptive Data Analytics Assignment Files.rar