Portfolio Dynamics for Customers of a Multi-Service Provider

Abstract:     
Multi-service providers, such as telecommunication and financial service companies, can benefit from understanding how customers' service portfolios evolve over the course of their relationships with a firm. This can provide guidance for managerial issues such as customer valuation and predicting customers' future behavior, whether it is acquiring additional services, selectively dropping current services, or ending the relationship entirely.

In this research, we develop a hidden Markov model to identify latent "relationship states" through which customers evolve, and demonstrate the importance of using customers' full subscription histories (e.g., their portfolio paths) to jointly model (and allow for correlation between) portfolio choice and duration. We then examine the relationship between state membership and managerially relevant metrics, including a customer's propensities for acquiring additional services or terminating the relationship, and CLV. Through a series of illustrative vignettes, we show that selective portfolio changes - both adding and dropping services - can lead to an increased likelihood of acquiring additional services at the time of the next portfolio change, a provocative finding of interest to service providers. Our findings also emphasize the need to look beyond the previous period, as utilized in much current research, and consider how customers have evolved over their entire relationship in order to predict their future actions.

Keywords: Hidden Markov Model, Customer Relationship Management

Working Paper Series