《Candy Crush Saga》中捆绑包推荐的尺度不变方法研究
On a Scale-Invariant Approach to Bundle Recommendations in Candy Crush Saga
AI总结:
针对移动游戏内容推荐需求,提出结合监督无监督方法的尺度不变捆绑包推荐方案,在《Candy Crush Saga》验证中实现点击率提升30%、领取率提升超40%,并量化了推荐精度对参与度的递减效应。
摘要:
深入理解玩家偏好对于提升内容相关性至关重要,在移动游戏领域尤其如此。本文阐述了注意力模型在移动游戏场景下生成物品推荐的应用。该方法结合了监督与无监督方法以生成用户级推荐,同时提出了一种新颖的尺度不变预测方法。随后该方法被应用于《Candy Crush Saga》的捆绑包推荐任务中。本文介绍了可扩展服务数百万用户的机器学习模型的部署、维护与监控策略,以及为降低机器学习系统典型技术债务所采用的最佳实践与设计模式。研究从离线和在线两方面对该推荐方法进行评估,重点分析用户参与度提升、点击率与领取率、新颖性效应、推荐多样性以及退化反馈循环的影响。实验证明,该推荐方法使点击率提升30%,领取率提升超40%。此外,本文还通过实证量化了推荐准确性对用户参与度的边际递减效应。
英文摘要:
A good understanding of player preferences is crucial for increasing content relevancy, especially in mobile games. This paper illustrates the use of attentive models for producing item recommendations in a mobile game scenario. The methodology comprises a combination of supervised and unsupervised approaches to create user-level recommendations while introducing a novel scale-invariant approach to the prediction. The methodology is subsequently applied to a bundle recommendation in Candy Crush Saga. The strategy of deployment, maintenance, and monitoring of ML models that are scaled up to serve millions of users is presented, along with the best practices and design patterns adopted to minimize technical debt typical of ML systems. The recommendation approach is evaluated both offline and online, with a focus on understanding the increase in engagement, click- and take rates, novelty effects, recommendation diversity, and the impact of degenerate feedback loops. We have demonstrated that the recommendation enhances user engagement by 30% concerning click rate and by more than 40% concerning take rate. In addition, we empirically quantify the diminishing effects of recommendation accuracy on user engagement.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。