CLVAE: A Variational Autoencoder for Long-Term Customer Revenue Forecasting

TL;DR

This paper introduces CLVAE, a variational autoencoder model that enhances long-term customer revenue forecasting by combining process-based likelihood with flexible latent representations, improving accuracy across diverse datasets.

Contribution

The paper presents a novel VAE-based approach that balances structural assumptions with flexible learning, enabling reliable and adaptable long-term customer revenue predictions.

Findings

Outperforms existing benchmarks on multiple datasets

Provides reliable forecasts even without contextual covariates

Flexibly incorporates rich covariates and nonlinear effects

Abstract

Predicting customers' long-term revenue from sparse and irregular transaction data is central to marketing resource allocation in non-contractual settings, yet existing approaches face a trade-off. Traditional probabilistic customer base models deliver robust long-horizon forecasts by imposing strong structural assumptions, while flexible machine-learning models often require substantial training data and careful tuning. We propose a variational-autoencoder-based model that preserves the process-based likelihood of established attrition-transaction-spend models conditional on customer heterogeneity, but replaces the restrictive parametric mixing distribution with a flexible latent representation learned by encoder-decoder networks. The resulting approach (i) provides a single model for customer attrition, transactions and spending, (ii) remains reliable when contextual covariates are unavailable, and (iii) flexibly incorporates rich covariates and nonlinear effects when they are available. This design balances structural stability with the flexibility needed to capture complex purchase dynamics. Across multiple real-world datasets and prediction horizons, the proposed model improves upon the latest benchmarks. Businesses benefit directly, as a better assessment of customers' future revenues improves the efficiency of campaign targeting. For research, this work provides guidance on how to embed domain-specific models into the variational autoencoder framework, enabling flexible representation learning while retaining an econometrically meaningful process structure.