Refer to Exercise 13 for a description of the data set. a. Create a boosting ensemble classification

Question:

Refer to Exercise 13 for a description of the data set.

a. Create a boosting ensemble classification tree model. What are the overall accuracy rate, sensitivity, and specificity of the model on the validation data? What is the AUC value of the model?

b. Compare the performance of the boosting ensemble model to that of the single-tree model created in Exercise 13 (for R) or Exercise 14 (for Analytic Solver). Which model shows more robust performance? Explain.

c. Score the two new cases in the Continue_Edu_Score worksheet using the boosting ensemble classification tree model. What is the probability of the first person enrolling in continuing education classes? What is the probability for the second person?

Data from Exercises 13

Samantha Brown is Director of Continuing Education of a major university. The Continuing Education department offers a wide range of five-week courses to the community during the summer. Samantha would like to find out which community members are more likely to enroll in these summer courses. She has compiled a data set of 2,000 community members that includes the following variables: age (Age), years of marriage (Marriage), annual income (Income), education level (Edu), whether the person owns his or her residence (Own), whether the person owns a pet (Pet), whether the person lives in the city or suburb (City), and whether the person has enrolled in at least one continuing education course from the university before (ContinueEdu, 1 = enrolled, 0 otherwise). A portion of the Continue_Edu_ Data worksheet is shown in the accompanying table. Build a default classification tree to predict whether a community member is likely to enroll in summer courses. Display the default classification tree.