SHORE: A Long-term User Lifetime Value Prediction Model in Digital Games

2025-06-12

AI Summary

In digital gaming scenarios, long-term user lifetime value (LTV) prediction faces three key challenges: payment latency, early-stage data sparsity, and outlier behavior among high-value users. Existing methods—relying on short-horizon observations or strong distributional assumptions—commonly suffer from systematic underestimation over extended horizons and poor robustness to outliers. To address these issues, we propose the first short-horizon auxiliary prediction framework specifically designed for LTV forecasting. Our approach jointly optimizes order-preserving multi-class classification and dynamic Huber loss to ensure ranking consistency and outlier robustness. Additionally, we incorporate multi-task learning and zero-inflated modeling to mitigate data sparsity and the heavy-tailed zero-inflation in payment distributions. Online A/B testing demonstrates that our method reduces relative prediction error by 47.91% compared to baseline models, significantly improving both accuracy and stability for long-horizon LTV estimation.

Technology Category

• Machine Learning: Online Learning & Bandits
• Game Theory and Economic Paradigms: Adversarial Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

In digital gaming, long-term user lifetime value (LTV) prediction is essential for monetization strategy, yet presents major challenges due to delayed payment behavior, sparse early user data, and the presence of high-value outliers. While existing models typically rely on either short-cycle observations or strong distributional assumptions, such approaches often underestimate long-term value or suffer from poor robustness. To address these issues, we propose SHort-cycle auxiliary with Order-preserving REgression (SHORE), a novel LTV prediction framework that integrates short-horizon predictions (e.g., LTV-15 and LTV-30) as auxiliary tasks to enhance long-cycle targets (e.g., LTV-60). SHORE also introduces a hybrid loss function combining order-preserving multi-class classification and a dynamic Huber loss to mitigate the influence of zero-inflation and outlier payment behavior. Extensive offline and online experiments on real-world datasets demonstrate that SHORE significantly outperforms existing baselines, achieving a 47.91% relative reduction in prediction error in online deployment. These results highlight SHORE's practical effectiveness and robustness in industrial-scale LTV prediction for digital games.

Problem

• Predict long-term user lifetime value in digital games
• Address delayed payment and sparse early user data
• Mitigate high-value outliers and zero-inflation effects

Innovation

• Integrates short-horizon predictions as auxiliary tasks
• Uses order-preserving multi-class classification loss
• Combines dynamic Huber loss for outlier robustness