|
Activity Number:
|
200
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 7, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics and Marketing
|
| Abstract - #307394 |
|
Title:
|
An Empirical Analysis of Customized and Dynamic Cross-Selling Campaigns
|
|
Author(s):
|
Alan Montgomery*+ and Baohong Sun and Shibo Li
|
|
Companies:
|
Carnegie Mellon University and Carnegie Mellon University and Indiana University
|
|
Address:
|
5000 Forbes Ave., Pittsburgh, PA, 15213,
|
|
Keywords:
|
marketing ; customer relationship management ; multivariate probit ; MCMC ; Bayesian ; customer lifetime value
|
|
Abstract:
|
The existing cross-selling literature has focused on developing methodologies to better predict purchase probabilities for the next product to be purchased. The usual goal is to find the best customers for a scheduled campaign. We formulate cross-selling campaigns as a stochastic dynamic programming problem that explicitly accounts for the company's long-term profit goal while taking into account the development of customer demand over time. The model yields optimal cross-selling strategies that are a multi-step, multi-segment and multi-channel cross-selling campaign process about when to target which consumer with what product using what campaign channel. Using cross-selling campaigns and transaction data provided by a national bank, we demonstrate the dynamic and state-dependent nature of the optimal cross-selling campaign decisions.
|
