Webinar: Efficient and Flexible Long-Tail Recommendation Using Cosine Patterns

Part of the Lubar Research Seminar Series

Speaker: Gedas Adomavicius, University of Minnesota

With the increasing use of recommender systems in various application domains, many algorithms have been proposed for improving the accuracy of recommendations. Among various other dimensions of recommender systems performance, long-tail (niche) recommendation performance remains an important challenge, due in large part to the popularity bias of many existing recommendation techniques. In this study, we propose CORE, a cosine-pattern-based technique, for effective long-tail recommendation. Comprehensive experimental results compare the proposed approach both to classical, widely-used recommendation algorithms and to specialized long-tail recommendation baselines, and demonstrate its practical benefits in accuracy, flexibility, and scalability, in addition to the superior long-tail recommendation performance.

Link: https://wisconsin-edu.zoom.us/j/95866539305?pwd=VFNiZDJWa3ZHb0xmY242bkpLRnVxZz09

Meeting ID: 958 6653 9305

Passcode: 094779