Raphael was interested in understanding the factors related to churn for a telco provider. The available database
Question:
Raphael was interested in understanding the factors related to churn for a telco provider. The available database had only a limited set of variables, so he was limited to looking at long distance, toll free, equipment, calling card, and wireless usage for the past month (all measured as scalar or metric variables) and whether the customer had multiple lines, voice mail, paging, internet, caller ID, call waiting, call forwarding, 3-way calling, and electronic billing services (measured as dummy yes/no variables). He ran a logistic regression with “churn last month” as the dependent variable and got the output displayed below.
i) (5 points) Why did Raphael decide to oversample customers who had churned last month to run the model?
ii) (5 points) Which variables appear to be significantly related to churn (if 0=no and 1=yes) at the .05 significance level?
iii) (4 points) Which factors appear to decrease the probability that a customer churned?
iv) (6 points) Outline the steps that Raphael might take to develop a churn management program using this model.
Financial Algebra advanced algebra with financial applications
ISBN: 978-0538449670
1st edition
Authors: Robert K. Gerver