Mini-Game Lifetime Value Prediction in WeChat

2025-05-21

AI Summary

In WeChat Mini-Game ecosystems, extremely low user purchase rates (∼0.1%) lead to severe scarcity of supervised signals for LTV prediction; meanwhile, multi-horizon tasks (e.g., 3-day/7-day/30-day LTV) are highly coupled, and error propagation across tasks degrades joint modeling accuracy. Method: We propose GRePO-LTV—a novel framework that unifies Pareto multi-objective optimization with graph representation learning. It employs a graph neural network to model sparse user behavioral relations and explicitly encodes inter-task dependencies to steer optimization toward the Pareto-optimal front. Contribution/Results: Evaluated on real-world mini-game data, GRePO-LTV achieves an 8.2% improvement in LTV prediction AUC and a 19.6% reduction in 30-day MAE, consistently outperforming state-of-the-art multi-task baselines. It establishes a new paradigm for joint multi-temporal LTV modeling under ultra-sparse supervision.

Technology Category

• Search and Optimization: Learning to Search
• Game Theory and Economic Paradigms: Cooperative Game Theory
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The LifeTime Value (LTV) prediction, which endeavors to forecast the cumulative purchase contribution of a user to a particular item, remains a vital challenge that advertisers are keen to resolve. A precise LTV prediction system enhances the alignment of user interests with meticulously designed advertisements, thereby generating substantial profits for advertisers. Nonetheless, this issue is complicated by the paucity of data typically observed in real-world advertising scenarios. The purchase rate among registered users is often as critically low as 0.1%, resulting in a dataset where the majority of users make only several purchases. Consequently, there is insufficient supervisory signal for effectively training the LTV prediction model. An additional challenge emerges from the interdependencies among tasks with high correlation. It is a common practice to estimate a user's contribution to a game over a specified temporal interval. Varying the lengths of these intervals corresponds to distinct predictive tasks, which are highly correlated. For instance, predictions over a 7-day period are heavily reliant on forecasts made over a 3-day period, where exceptional cases can adversely affect the accuracy of both tasks. In order to comprehensively address the aforementioned challenges, we introduce an innovative framework denoted as Graph-Represented Pareto-Optimal LifeTime Value prediction (GRePO-LTV). Graph representation learning is initially employed to address the issue of data scarcity. Subsequently, Pareto-Optimization is utilized to manage the interdependence of prediction tasks.

Problem

• Predicting user purchase contributions in WeChat mini-games accurately
• Addressing data scarcity in real-world advertising scenarios
• Managing interdependencies among highly correlated prediction tasks

Innovation

• Graph representation learning for data scarcity
• Pareto-Optimization for task interdependence
• GRePO-LTV framework for LTV prediction