Dual-Phase Playtime-guided Recommendation: Interest Intensity Exploration and Multimodal Random Walks

TL;DR

This paper introduces DP2Rec, a recommendation system for video games that leverages playtime and multimodal data to improve both accuracy and diversity of recommendations through dual-phase interest modeling and guided random walks.

Contribution

The paper proposes a novel dual-phase model that utilizes playtime signals and multimodal information for enhanced gaming recommendations, addressing limitations of prior approaches.

Findings

DP2Rec outperforms existing methods in accuracy.

DP2Rec improves recommendation diversity.

The model effectively captures user preferences through dual-beta interest modeling.

Abstract

The explosive growth of the video game industry has created an urgent need for recommendation systems that can scale with expanding catalogs and maintain user engagement. While prior work has explored accuracy and diversity in recommendations, existing models underutilize playtime, a rich behavioral signal unique to gaming platforms, and overlook the potential of multimodal information to enhance diversity. In this paper, we propose DP2Rec, a novel Dual-Phase Playtime-guided Recommendation model designed to jointly optimize accuracy and diversity. First, we introduce a playtime-guided interest intensity exploration module that separates strong and weak preferences via dual-beta modeling, enabling fine-grained user profiling and more accurate recommendations. Second, we present a playtime-guided multimodal random walks module that simulates player exploration using transitions guided by both playtime-derived interest similarity and multimodal semantic similarity. This mechanism preserves core preferences while promoting cross-category discovery through latent semantic associations and adaptive category balancing. Extensive experiments on a real-world game dataset show that DP2Rec outperforms existing methods in both recommendation accuracy and diversity.