Network Friendly Recommendations: Optimizing for Long Viewing Sessions

TL;DR

This paper introduces an optimal polynomial-time algorithm for recommendation systems that optimize long-term network costs while maintaining high recommendation quality, demonstrating significant improvements over baseline methods.

Contribution

It presents the first polynomial-time algorithm for recommendation-driven request sequences that balances network cost and recommendation quality, including position preferences.

Findings

2x improvement over baseline recommendations

80% reduction in network cost compared to greedy approaches

Maintains at least 90% of original recommendation quality

Abstract

Caching algorithms try to predict content popularity, and place the content closer to the users. Additionally, nowadays requests are increasingly driven by recommendation systems (RS). These important trends, point to the following: \emph{make RSs favor locally cached content}, this way operators reduce network costs, and users get better streaming rates. Nevertheless, this process should preserve the quality of the recommendations (QoR). In this work, we propose a Markov Chain model for a stochastic, recommendation-driven \emph{sequence} of requests, and formulate the problem of selecting high quality recommendations that minimize the network cost \emph{in the long run}. While the original optimization problem is non-convex, it can be convexified through a series of transformations. Moreover, we extend our framework for users who show preference in some positions of the recommendations' list. To our best knowledge, this is the first work to provide an optimal polynomial-time algorithm for these problems. Finally, testing our algorithms on real datasets suggests significant potential, e.g., $2\times$ improvement compared to baseline recommendations, and 80\% compared to a greedy network-friendly-RS (which optimizes the cost for I.I.D. requests), while preserving at least 90\% of the original QoR. Finally, we show that taking position preference into account leads to additional performance gains.