Tasks to do: The task is to predict if the auction will be competitive. Step 1: Create pivot tables for the average of the binary dependent variable (Competitive?) as a function of the various categorical variables (use the original variables, not the dummies). Use the information in the tables to reduce the number of dummies that will be used in the model. For example, categories that appear most similar with respect to the distribution of competitive auctions could be combined. For Pivot tables, create 4 pivot tables as below ( in one worksheet if possible): Row label: Category Value: Average of Competitiveness Row Label: Duration Row Label: Currency Row Label: endDay Modify the original data as below: Value: Average of Competitiveness Value: Average of Competitiveness Value: Average of Competitiveness 1. Replace Collectibles by Antique/Art/Craft in the original data. 2. Replace Business/Industrial by Computer in the original data 3. Replace Sun and Fri by Sun_Fri in the original data. DA 540 Applied Data Mining Dr. Annadatha [For your understanding, the above data modifications are justified for the following reasons: From the pivot table, you can see the following: The categories "Business/Industrials" and "Computers" have same average of the binary variable "competitive." This means that the percentage of competitive auctions in each of these two categories is equal