Beyond Collaborative Filtering: A Relook at Task Formulation in Recommender Systems
arXiv:2404.13375 · doi:10.1145/3663752.3663756
Abstract
Recommender Systems (RecSys) have become indispensable in numerous applications, profoundly influencing our everyday experiences. Despite their practical significance, academic research in RecSys often abstracts the formulation of research tasks from real-world contexts, aiming for a clean problem formulation and more generalizable findings. However, it is observed that there is a lack of collective understanding in RecSys academic research. The root of this issue may lie in the simplification of research task definitions, and an overemphasis on modeling the decision outcomes rather than the decision-making process. That is, we often conceptualize RecSys as the task of predicting missing values in a static user-item interaction matrix, rather than predicting a user's decision on the next interaction within a dynamic, changing, and application-specific context. There exists a mismatch between the inputs accessible to a model and the information available to users during their decision-making process, yet the model is tasked to predict users' decisions. While collaborative filtering is effective in learning general preferences from historical records, it is crucial to also consider the dynamic contextual factors in practical settings. Defining research tasks based on application scenarios using domain-specific datasets may lead to more insightful findings. Accordingly, viable solutions and effective evaluations can emerge for different application scenarios.
Published in ACM SIGWEB Newsletter, Spring 2024: https://dl.acm.org/doi/10.1145/3663752.3663756
References in corpus (10)
- Take a Fresh Look at Recommender Systems from an Evaluation Standpoint
- DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
- The Effect of Third Party Implementations on Reproducibility
- Dataset vs Reality: Understanding Model Performance from the Perspective of Information Need
- On the Generalizability and Predictability of Recommender Systems
- A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)
- Recommender for Its Purpose: Repeat and Exploration in Food Delivery Recommendations
- Our Model Achieves Excellent Performance on MovieLens: What Does it Mean?
- RecBaselines2023: a new dataset for choosing baselines for recommender models
- Retraining A Graph-based Recommender with Interests Disentanglement