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

TL;DR

SHORE is a novel framework for long-term user lifetime value prediction in digital games, combining short-term auxiliary tasks with a hybrid loss to improve accuracy and robustness over existing models.

Contribution

It introduces a new LTV prediction model that integrates short-horizon predictions and a hybrid loss function to better handle delayed payments and outliers.

Findings

Achieves a 47.91% reduction in prediction error online.

Outperforms existing baselines in offline and online experiments.

Demonstrates robustness and practical effectiveness in industrial-scale deployment.

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.