Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation

TL;DR

This paper introduces PARE, a non-personalized recommendation model that predicts popular items by modeling temporal popularity trends, offering a simple yet effective alternative or complement to personalized recommender systems.

Contribution

The paper presents PARE, the first model explicitly capturing item popularity dynamics for recommendation, which can enhance existing personalized methods and is practical for industrial use.

Findings

PARE matches or outperforms state-of-the-art recommenders.

Integrating PARE with existing methods improves overall performance.

PARE's simplicity makes it suitable for real-world applications.

Abstract

Recommender systems have been gaining increasing research attention over the years. Most existing recommendation methods focus on capturing users' personalized preferences through historical user-item interactions, which may potentially violate user privacy. Additionally, these approaches often overlook the significance of the temporal fluctuation in item popularity that can sway users' decision-making. To bridge this gap, we propose Popularity-Aware Recommender (PARE), which makes non-personalized recommendations by predicting the items that will attain the highest popularity. PARE consists of four modules, each focusing on a different aspect: popularity history, temporal impact, periodic impact, and side information. Finally, an attention layer is leveraged to fuse the outputs of four modules. To our knowledge, this is the first work to explicitly model item popularity in recommendation systems. Extensive experiments show that PARE performs on par or even better than sophisticated state-of-the-art recommendation methods. Since PARE prioritizes item popularity over personalized user preferences, it can enhance existing recommendation methods as a complementary component. Our experiments demonstrate that integrating PARE with existing recommendation methods significantly surpasses the performance of standalone models, highlighting PARE's potential as a complement to existing recommendation methods. Furthermore, the simplicity of PARE makes it immensely practical for industrial applications and a valuable baseline for future research.