Personalized Bundle Recommendation in Online Games

TL;DR

This paper introduces a neural network-based bundle recommendation system for online games, formalized as link prediction on a tripartite graph, significantly improving conversion rates and GMV in a real-world deployment.

Contribution

It formalizes bundle recommendation as a link prediction problem on a user-item-bundle graph and demonstrates its effectiveness through extensive experiments and real-world deployment.

Findings

Over 60% increase in bundle conversion rate

More than 15% improvement in GMV

Effective in both public datasets and industrial setting

Abstract

In business domains, \textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers. Existing recommender systems mostly focus on recommending individual items that users may be interested in. In this paper, we target at a practical but less explored recommendation problem named bundle recommendation, which aims to offer a combination of items to users. To tackle this specific recommendation problem in the context of the \emph{virtual mall} in online games, we formalize it as a link prediction problem on a user-item-bundle tripartite graph constructed from the historical interactions, and solve it with a neural network model that can learn directly on the graph-structure data. Extensive experiments on three public datasets and one industrial game dataset demonstrate the effectiveness of the proposed method. Further, the bundle recommendation model has been deployed in production for more than one year in a popular online game developed by Netease Games, and the launch of the model yields more than 60\% improvement on conversion rate of bundles, and a relative improvement of more than 15\% on gross merchandise volume (GMV).