A Re-visit of the Popularity Baseline in Recommender Systems

Abstract

Popularity is often included in experimental evaluation to provide a reference performance for a recommendation task. To understand how popularity baseline is defined and evaluated, we sample 12 papers from top-tier conferences including KDD, WWW, SIGIR, and RecSys, and 6 open source toolkits. We note that the widely adopted MostPop baseline simply ranks items based on the number of interactions in the training data. We argue that the current evaluation of popularity (i) does not reflect the popular items at the time when a user interacts with the system, and (ii) may recommend items released after a user's last interaction with the system. On the widely used MovieLens dataset, we show that the performance of popularity could be significantly improved by 70% or more, if we consider the popular items at the time point when a user interacts with the system. We further show that, on MovieLens dataset, the users having lower tendencies on movies tend to follow the crowd and rate more popular movies. Movie lovers who rate a large number of movies, rate movies based on their own preferences and interests. Through this study, we call for a re-visit of the popularity baseline in recommender system to better reflect its effectiveness.

arXiv commentAccepted by SIGIR2020

References in corpus (2)

• Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
• Microsoft Recommenders: Tools to Accelerate Developing Recommender Systems

Cited by in corpus (15)

• Causal Intervention for Leveraging Popularity Bias in Recommendation
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• A Critical Study on Data Leakage in Recommender System Offline Evaluation
• gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling
• Take a Fresh Look at Recommender Systems from an Evaluation Standpoint
• It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences Are Dynamic
• Debiasing Recommendation with Personal Popularity
• Revisiting BPR: A Replicability Study of a Common Recommender System Baseline
• Intent Disentanglement and Feature Self-supervision for Novel Recommendation
• Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation
• A Pre-trained Sequential Recommendation Framework: Popularity Dynamics for Zero-shot Transfer
• Peer Recommendation Interventions for Health-related Social Support: a Feasibility Assessment
• Rolling Forward: Enhancing LightGCN with Causal Graph Convolution for Credit Bond Recommendation
• Towards Proactively Forecasting Sentence-Specific Information Popularity within Online News Documents
• Cyberswarm: a novel swarm intelligence algorithm inspired by cyber community dynamics