用改进的Transformer模型更准预测玩家游戏付费意愿。
Efficient Feature Interactions with Transformers: Improving User Spending Propensity Predictions in Gaming
- 设计新架构捕捉特征间复杂交互
- MAE降低2.5%，MSE降低21.8%
- 适合游戏平台个性化推荐与促活
Dream11 是一个拥有超2亿用户的幻想体育平台，提供多种真实体育赛事的竞猜活动。在真实金钱游戏场景中，用户需支付入场费参与各类竞赛产品。本文聚焦于预测用户在单轮游戏中付费意愿的任务，以支持后续应用如精准激励、个性化产品推荐等。基于历史交易数据建模用户付费倾向，我们对比了树模型与深度学习模型的表现，并提出一种专为结构化数据设计的新架构。该模型通过增强特征交互能力，在预测用户付费意愿任务上优于现有方法。实验表明，新提出的Transformer模型超越当前最优的FT-Transformer，在MAE上提升2.5%，在MSE上提升21.8%。
原文摘要 · Abstract (English)
Dream11 is a fantasy sports platform that allows users to create their own virtual teams for real-life sports events. We host multiple sports and matches for our 200M+ user base. In this RMG (real money gaming) setting, users pay an entry amount to participate in various contest products that we provide to users. In our current work, we discuss the problem of predicting the user's propensity to spend in a gaming round, so it can be utilized for various downstream applications. e.g. Upselling users by incentivizing them marginally as per their spending propensity, or personalizing the product listing based on the user's propensity to spend. We aim to model the spending propensity of each user based on past transaction data. In this paper, we benchmark tree-based and deep-learning models that show good results on structured data, and we propose a new architecture change that is specifically designed to capture the rich interactions among the input features. We show that our proposed architecture outperforms the existing models on the task of predicting the user's propensity to spend in a gaming round. Our new transformer model surpasses the state-of-the-art FT-Transformer, improving MAE by 2.5\% and MSE by 21.8\%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。