1. Summarize (in plain English) the C&RT model's predictions for who are buyers (for example, males who have made more than 3 purchases and at least one art books are predicted to be buyers, etc.) 2. Summarize key results from the risk table and gains summary. 3. Use the information in the gains summary to make a 'banana' gains chart. 4. Profitability Analysis: Because we oversampled the buyers we need to make some adjustments to assess the profitability of using this approach. Our prior approach of targeting individuals or groups with a probability of purchase of 8.3% or better is not useful here (since we now have 45% buyers, virtually all groups will exceed this hurdle). Since all buyers are included in the dataset. we know (from the risk table) how many would be predicted to be buyers. Similarly, we can compute the proportion of non- buyers that the model incorrectly predicts to be buyers. Use this along with the same costs as before ($18 selling price, $9 wholesale price, $3 shipping and $0.50 mailing costs) to estimate what the gross profit (in dollars and as a % of gross sales) and return on marketing would be if the "The Art History of Florence' offer were only mailed to those predicted by the C&RT decision tree to be buyers