Automatic Collection Creation and Recommendation

TL;DR

This paper introduces a novel collection recommender system that automatically creates themed item collections for users, significantly increasing consumption and diversity in music streaming services.

Contribution

It presents a new approach to generate user-specific collections using clustering and heuristics, advancing beyond traditional item-based recommendations.

Findings

2.3x increase in recommendation-driven consumption

Improved utilization of display space and diversity

First large-scale experiments of this kind

Abstract

We present a collection recommender system that can automatically create and recommend collections of items at a user level. Unlike regular recommender systems, which output top-N relevant items, a collection recommender system outputs collections of items such that the items in the collections are relevant to a user, and the items within a collection follow a specific theme. Our system builds on top of the user-item representations learnt by item recommender systems. We employ dimensionality reduction and clustering techniques along with intuitive heuristics to create collections with their ratings and titles. We test these ideas in a real-world setting of music recommendation, within a popular music streaming service. We find that there is a 2.3x increase in recommendation-driven consumption when recommending collections over items. Further, it results in effective utilization of real estate and leads to recommending a more and diverse set of items. To our knowledge, these are first of its kind experiments at such a large scale.