Reducing offline evaluation bias of collaborative filtering algorithms
This addresses a specific issue in recommendation systems for online platforms, but appears incremental as it applies an existing method to a known problem.
The paper tackles the problem of offline evaluation bias in collaborative filtering algorithms for recommendation systems, presenting a new application of weighted offline evaluation to reduce this bias.
Recommendation systems have been integrated into the majority of large online systems to filter and rank information according to user profiles. It thus influences the way users interact with the system and, as a consequence, bias the evaluation of the performance of a recommendation algorithm computed using historical data (via offline evaluation). This paper presents a new application of a weighted offline evaluation to reduce this bias for collaborative filtering algorithms.