Abstract Details
Activity Number:
|
403
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Statistics in Marketing
|
Abstract #311098
|
|
Title:
|
Some Customers Rather Leave Without Saying Goodbye
|
Author(s):
|
Eva Ascarza*+ and Oded Netzer and Bruce G.S. Hardie
|
Companies:
|
Columbia Business School and Columbia Business School and London Business School
|
Keywords:
|
Hidden Markov Model ;
Churn / Retention ;
Customer Base Analysis ;
Predictive Models ;
Customer Analytics ;
Bayesian
|
Abstract:
|
We develop a dynamic latent variable model to study not only when, but also how, customers churn. In particular, we analyze the case in which companies might, but not necessarily do, observe customer attrition. This occurs in many online settings where customers have the choice to stop interacting with the firm either by formally terminating the relationship (e.g., canceling the account) or by simply ignoring all communications coming from the firm.
Our model incorporates both types of attrition by assuming an individual-level latent variable that evolves over time. We capture the dynamics in the latent variable using a hidden Markov model and allow for unobserved heterogeneity across individuals in the transition process. The model parameters are estimated using hierarchical Bayesian methods. We apply the model in the context of a web-based deals site, where multiple sources of daily usage/activity (e.g., e-mail openings, clicks) as well as unsubscription behavior are observed. We find substantial differences in usage behavior between those customers who 'visibly' churn and those who do it 'silently'. We discuss methodological and managerial implications of this research.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.