This pro- for both instructors and students on how to register for and access Analytic Solver. PROBLEMS AND EXERCISES 1. Compute the Euclidean distance between the following 5. Using only Credit Score, Years of Credit History, Revolving Balance, and Revolving Utilization, Cluster Analysis apply single linkage cluster analysis to the first six records in the Excel file Credit Approval Decisions and draw a dendogram illustrating the clustering process. 6. Apply single linkage cluster analysis to the first five records in the Excel file Sales Data, using the vari- ables Percent Gross Profit, Industry Code, and Com- petitive Rating, and draw a dendogram illustrating the clustering process. a a sets of points: a. (2,5) and (8,4) b. (12.-1, 32) and (18, 15, -52) 2. For the Excel file Colleges and Universities Cluster Analysis Worksheet, compute the normalized Euclid- can distances between Berkeley, Cal Tech, UCLA, and UNC, and illustrate the results in a distance matrix. 3. For the three clusters identified in Table 10.3, find the average and standard deviations of each numerical variable for the schools in each cluster and compare them with the average and standard deviation for the entire data set. Does the clustering show distinct dif- ferences among these clusters? 4. In Problem 2, you found a normalized distance matrix between Berkeley, Cal Tech, UCLA, and UNC for the Excel file Colleges and Universities Cluster Analysis Worksheet. Apply single linkage clustering to these schools and draw a dendogram illustrating the clus- Classification 7. Using the approach described in Example 10.6, clas- sify first record in the worksheet Records to Classify in the Excel file Credit Risk Data using the k-NN algorithm for k = 1 to 5. Use only Checking, Savings, Months Customer, and Months Employed. 8. Use the k-NN algorithm to classify the new records in the Excel file Credit Approval Decisions Classifica- tion Data using only Credit Score and Years of Credit History for k = 1 to 5. 9. Use discriminant analysis to classify the new records in the Excel file Credit Approval Decisions Discrimi- nant Analysis using only Credit Score and Years of Credit History as input variables. tering process. Rule 1: If Fastest Engine, then Traction Control 376 Chapter 10 Introduction to Data Mining 10. Extract the records for business loans in the Excel file Credit Risk Data and code the non-numerical data. Rule 2: If Faster Engine and 16-inch Wheels, then Apply discriminant analysis to classify the credit Year Warranty risk for the business loans in the Records to Classify worksheet Compute the support, confidence, and lift for each of these rules. Association 11. The Excel file Automobile Options provides data on Cause and Effect Modeling options ordered together for a particular model of 13. The Excel file Myatt Steak House provides five years automobile. By examining the correlation matrix, of data on key business results for a restaurant. Ider- suggest some associations. tify the leading and lagging measures, find the come 12. The Excel file Automobile Options provides data on lation matrix, and propose a cause-and-effect model options ordered together for a particular model of using the strongest correlations. automobile. Consider the following rules: CASE: PERFORMANCE LAWN EQUIPMENT he worksheet Purchasing Survey in the Performance Lawn Care Database provides data related to predicti the level of Usgee law