CB2CF: A Neural Multiview Content-to-Collaborative Filtering Model for Completely Cold Item Recommendations
This work addresses the cold-start problem in recommender systems for services like Microsoft Store, which serves around a billion users, though it appears incremental as it builds on existing CF and CB methods.
The paper tackles the problem of recommending completely cold items by bridging content-based and collaborative filtering approaches, resulting in a model that outperforms an alternative content-based model on movies and apps recommendations.
In Recommender Systems research, algorithms are often characterized as either Collaborative Filtering (CF) or Content Based (CB). CF algorithms are trained using a dataset of user preferences while CB algorithms are typically based on item profiles. These approaches harness different data sources and therefore the resulting recommended items are generally very different. This paper presents the CB2CF, a deep neural multiview model that serves as a bridge from items content into their CF representations. CB2CF is a real-world algorithm designed for Microsoft Store services that handle around a billion users worldwide. CB2CF is demonstrated on movies and apps recommendations, where it is shown to outperform an alternative CB model on completely cold items.