Working Paper

A Scalable Recommendation Engine for New Users and Items

Yiting Deng

University College London

Carl F. Mela

Duke University

Boya Xu

Duke University

Oct 20, 2022


Develops and tests a recommendation engine that extends collaborative filtering with demographic and item attributes and uses multi-armed bandit techniques to reveal consumer preferences to overcome the challenge of “cold-starts” with little or no prior data and problems of scale associated with multiple users and attributes.

By using you agree to our use of cookies as identifiers and for other features of the site as described in our Privacy Policy.