Deconvolving Feedback Loops in Recommender Systems

Abstract

Collaborative filtering is a popular technique to infer users' preferences on new content based on the collective information of all users preferences. Recommender systems then use this information to make personalized suggestions to users. When users accept these recommendations it creates a feedback loop in the recommender system, and these loops iteratively influence the collaborative filtering algorithm's predictions over time. We investigate whether it is possible to identify items affected by these feedback loops. We state sufficient assumptions to deconvolve the feedback loops while keeping the inverse solution tractable. We furthermore develop a metric to unravel the recommender system's influence on the entire user-item rating matrix. We use this metric on synthetic and real-world datasets to (1) identify the extent to which the recommender system affects the final rating matrix, (2) rank frequently recommended items, and (3) distinguish whether a user's rated item was recommended or an intrinsic preference. Our results indicate that it is possible to recover the ratings matrix of intrinsic user preferences using a single snapshot of the ratings matrix without any temporal information.

Neural Information Processing Systems, 2016

Cited by in corpus (16)

• Advances and Challenges in Conversational Recommender Systems: A Survey
• A Graph-based Approach for Mitigating Multi-sided Exposure Bias in Recommender Systems
• Optimal Decision Making Under Strategic Behavior
• Multi-sided Exposure Bias in Recommendation
• Unbiased Cascade Bandits: Mitigating Exposure Bias in Online Learning to Rank Recommendation
• Beyond Ads: Sequential Decision-Making Algorithms in Law and Public Policy
• Towards Fair Personalization by Avoiding Feedback Loops
• Disentangling User Interest and Conformity for Recommendation with Causal Embedding
• Recovering Markov Models from Closed-Loop Data
• Do Offline Metrics Predict Online Performance in Recommender Systems?
• Spatial Positioning Token (SPToken) for Smart Mobility
• Analysis of hidden feedback loops in continuous machine learning systems
• Consequential Ranking Algorithms and Long-term Welfare
• Competing AI: How does competition feedback affect machine learning?
• Correcting Exposure Bias for Link Recommendation
• Action-conditional Sequence Modeling for Recommendation