Contrastive Multi-view Framework for Customer Lifetime Value Prediction

TL;DR

This paper introduces a contrastive multi-view framework for customer lifetime value prediction that enhances robustness and accuracy by combining multiple regressors and contrastive learning, especially effective with limited data.

Contribution

It proposes a novel multi-view, contrastive learning-based framework for LTV prediction that improves robustness and performance over traditional single-view methods.

Findings

Achieved 32.26% increase in total payment amount in real-world deployment.

Validated effectiveness through extensive experiments on a game LTV dataset.

Demonstrated robustness and improved accuracy with limited training samples.

Abstract

Accurate customer lifetime value (LTV) prediction can help service providers optimize their marketing policies in customer-centric applications. However, the heavy sparsity of consumption events and the interference of data variance and noise obstruct LTV estimation. Many existing LTV prediction methods directly train a single-view LTV predictor on consumption samples, which may yield inaccurate and even biased knowledge extraction. In this paper, we propose a contrastive multi-view framework for LTV prediction, which is a plug-and-play solution compatible with various backbone models. It synthesizes multiple heterogeneous LTV regressors with complementary knowledge to improve model robustness and captures sample relatedness via contrastive learning to mitigate the dependency on data abundance. Concretely, we use a decomposed scheme that converts the LTV prediction problem into a combination of estimating consumption probability and payment amount. To alleviate the impact of noisy data on model learning, we propose a multi-view framework that jointly optimizes multiple types of regressors with diverse characteristics and advantages to encode and fuse comprehensive knowledge. To fully exploit the potential of limited training samples, we propose a hybrid contrastive learning method to help capture the relatedness between samples in both classification and regression tasks. We conduct extensive experiments on a real-world game LTV prediction dataset and the results validate the effectiveness of our method. We have deployed our solution online in Huawei's mobile game center and achieved 32.26% of total payment amount gains.