Bookbinder's case questions.

BBBC is evaluating two different modeling methods to isolate the factors that most influenced

customers to order The Art History of Florence: a binary logit model and an ordinary linear regression

model.

1. Open the case of BookBinders Club on Enginius. Provide an interpretation of the model

coefficient estimates - which factors were most important in driving an individual's decision to

make a purchase in response to receiving a mailing? (10 points)

2. Bookbinders is considering a similar mail campaign in the Midwest where it has data for 50,000

customers. Such mailings typically promote several books. The allocated cost of the mailing is

$0.65/addressee (including postage) for the art book, and the book costs Bookbinders $15 to

purchase and mail. The company allocates overhead to each book at 45 percent of cost. The

selling price of the book is $31.95.

a. Does the lift chart suggest that using a model-based approach can improve profits,

relative to a random targeting approach? Briefly explain your answer. (5 points)

b. Suppose that BookBinders Book Club is deciding on how many deciles of the market to

target (e.g., 10%, 20%, 30%, etc). If BBBC is using the logit model to make this decision,

how many deciles should it target? (10 points)

c. Given your answer to part b), how much more profit would you expect BBBC to make

from the model-based targeting approach, relative to mailing all 50,000 customers in

the mailing list. (5 points)

3. Repeat questions 1) and 2) using a regression model, instead of a logit model. Are your results

significantly different when you use the regression model? (Hint: instead of running the

regression on excel, you can choose to choose the target variable to be continuous on Enginius)

(20 points)

4. Based on the insights you gained from this modeling exercise, summarize the advantages and

limitations of the two modeling approaches. Look at both similar and dissimilar results (10

points)