The Universal Recommender

TL;DR

The paper introduces the Universal Recommender, a versatile system capable of applying to any semantic dataset, unifying various domain-specific recommenders through a scalable architecture and novel machine learning techniques.

Contribution

It presents a general recommender system architecture that extends to any semantic dataset, incorporating new machine learning methods for improved accuracy.

Findings

Successfully applied to IPTV data

Identified novel machine learning optimization problems

Demonstrated scalability and versatility

Abstract

We describe the Universal Recommender, a recommender system for semantic datasets that generalizes domain-specific recommenders such as content-based, collaborative, social, bibliographic, lexicographic, hybrid and other recommenders. In contrast to existing recommender systems, the Universal Recommender applies to any dataset that allows a semantic representation. We describe the scalable three-stage architecture of the Universal Recommender and its application to Internet Protocol Television (IPTV). To achieve good recommendation accuracy, several novel machine learning and optimization problems are identified. We finally give a brief argument supporting the need for machine learning recommenders.