Predicting Customer Lifetime Value Using Recurrent Neural Net

TL;DR

This paper presents a recurrent neural network model that effectively predicts customer lifetime value in SaaS applications by incorporating multiple time dimensions, outperforming traditional models in accuracy.

Contribution

Introduces a multi-dimensional RNN approach for customer lifetime value prediction, capturing cohort, age-in-system, and calendar time effects.

Findings

Significantly improves median absolute percent error over baseline models.

Effective for both new user acquisition and existing user retention predictions.

Applicable across various time horizons.

Abstract

This paper introduces a recurrent neural network approach for predicting user lifetime value in Software as a Service (SaaS) applications. The approach accounts for three connected time dimensions. These dimensions are the user cohort (the date the user joined), user age-in-system (the time since the user joined the service) and the calendar date the user is an age-in-system (i.e., contemporaneous information).The recurrent neural networks use a multi-cell architecture, where each cell resembles a long short-term memory neural network. The approach is applied to predicting both acquisition (new users) and rolling (existing user) lifetime values for a variety of time horizons. It is found to significantly improve median absolute percent error versus light gradient boost models and Buy Until You Die models.