A Generalized Framework for Estimating Customer Lifetime Value When Customer Lifetimes are Not Observed

Abstract

Measuring customer lifetime value (CLV) in contexts where customer defections are not observed, i.e. noncontractual contexts, has been very challenging for firms. This paper proposes a flexible Generalized Simulation-based estimation Framework (GSF) for predicting lifetimes and measuring customer lifetime value (CLV) in such contexts.

In the literature, two existing state-of-the-art models for lifetime value calculations in a noncontractual context are the Pareto/NBD and the BG/NBD models. Both the Pareto/NBD and the BG/NBD models are based on fixed underlying assumptions about drivers of CLV that cannot be changed even in situations where the firm believes that these assumptions are violated. The proposed GSF (not being a model per se, but a flexible estimation framework) allows the user to use any of the commonly available statistical distributions for the drivers of CLV, and thus the multitude of models that can be estimated using the GSF (the Pareto/NBD and the BG/NBD models included) is limited only by the availability of statistical distributions.

This flexibility is demonstrated in an empirical application where three additional models (in addition to the Pareto/NBD and BG/NBD) are estimated and a comparative predictive performance (in predicting customer lifetimes and CLV) of all the five models carried out. Further the GSF is used to estimate a sixth CLV model with covariates and correlations across the drivers of CLV. Thus potential users of the Pareto/NBD and BG/NBD models now have a flexible framework which allows them to estimate a multitude of models (in addition to these two models). In addition, the GSF allows users to incorporate covariates and correlations across outcomes in assessing lifetime values of their customers.

Keywords: Customer Lifetime Value, Pareto/NBD, BG/NBD, Forecasting, Simulation, Data Augmentation, MCMC methods

JEL Classification: C1, C3, C5