A Scalable Recommendation Engine for New Users and Items
This addresses the challenge of making scalable recommendations for new users and items in domains like online news and e-tailing, though it appears incremental as it combines existing techniques.
The paper tackled the cold-start problem in recommendation systems by introducing CFB-A, which integrates collaborative filtering, multi-armed bandits, and attributes, resulting in substantial improvements in cumulative average rewards like clicks and purchases compared to baseline methods.
In many digital contexts such as online news and e-tailing with many new users and items, recommendation systems face several challenges: i) how to make initial recommendations to users with little or no response history (i.e., cold-start problem), ii) how to learn user preferences on items (test and learn), and iii) how to scale across many users and items with myriad demographics and attributes. While many recommendation systems accommodate aspects of these challenges, few if any address all. This paper introduces a Collaborative Filtering (CF) Multi-armed Bandit (B) with Attributes (A) recommendation system (CFB-A) to jointly accommodate all of these considerations. Empirical applications including an offline test on MovieLens data, synthetic data simulations, and an online grocery experiment indicate the CFB-A leads to substantial improvement on cumulative average rewards (e.g., total money or time spent, clicks, purchased quantities, average ratings, etc.) relative to the most powerful extant baseline methods.