Reducing Offline Evaluation Bias in Recommendation Systems
This addresses a critical issue for developers and researchers in recommendation systems, though it is incremental as it builds on existing bias reduction methods.
The paper tackled the problem of evaluation bias in offline assessment of recommendation systems, proposing a simple item weighting solution that reduced bias impact, with efficiency demonstrated on real-world data from Viadeo professional social network.
Recommendation systems have been integrated into the majority of large online systems. They tailor those systems to individual users by filtering and ranking information according to user profiles. This adaptation process influences the way users interact with the system and, as a consequence, increases the difficulty of evaluating a recommendation algorithm with historical data (via offline evaluation). This paper analyses this evaluation bias and proposes a simple item weighting solution that reduces its impact. The efficiency of the proposed solution is evaluated on real world data extracted from Viadeo professional social network.