Sequential Recommendation in Online Games with Multiple Sequences, Tasks and User Levels

TL;DR

This paper introduces M$^3$Rec, a novel sequential recommendation model for online games that handles multiple sequences, tasks, and user levels, leveraging graph neural networks and multi-task learning to improve recommendation quality.

Contribution

The paper presents M$^3$Rec, the first model to effectively incorporate multiple sequences, tasks, and user levels in online game recommendations using GNNs and multi-task learning.

Findings

M$^3$Rec outperforms existing methods in offline evaluations.

M$^3$Rec improves online recommendation accuracy.

The model effectively captures complex user behavior in online games.

Abstract

Online gaming is growing faster than ever before, with increasing challenges of providing better user experience. Recommender systems (RS) for online games face unique challenges since they must fulfill players' distinct desires, at different user levels, based on their action sequences of various action types. Although many sequential RS already exist, they are mainly single-sequence, single-task, and single-user-level. In this paper, we introduce a new sequential recommendation model for multiple sequences, multiple tasks, and multiple user levels (abbreviated as M$^3$Rec) in Tencent Games platform, which can fully utilize complex data in online games. We leverage Graph Neural Network and multi-task learning to design M$^3$Rec in order to model the complex information in the heterogeneous sequential recommendation scenario of Tencent Games. We verify the effectiveness of M$^3$Rec on three online games of Tencent Games platform, in both offline and online evaluations. The results show that M$^3$Rec successfully addresses the challenges of recommendation in online games, and it generates superior recommendations compared with state-of-the-art sequential recommendation approaches.