SOBA: Session optimal MDP-based network friendly recommendations

TL;DR

This paper introduces SOBA, an MDP-based framework for network-friendly recommendations that optimizes user session costs and recommendation quality, outperforming existing methods in efficiency and scalability.

Contribution

The paper presents a novel MDP formulation for network-friendly recommendations, unifying and extending prior models with improved efficiency and scalability.

Findings

MDP approach outperforms myopic algorithms in session cost and recommendation quality

The framework is significantly faster, 10 times more efficient than state-of-the-art algorithms

The approach scales better with content catalog and batch sizes

Abstract

Caching content over CDNs or at the network edge has been solidified as a means to improve network cost and offer better streaming experience to users. Furthermore, nudging the users towards low-cost content has recently gained momentum as a strategy to boost network performance. We focus on the problem of optimal policy design for Network Friendly Recommendations (NFR). We depart from recent modeling attempts, and propose a Markov Decision Process (MDP) formulation. MDPs offer a unified framework that can model a user with random session length. As it turns out, many state-of-the-art approaches can be cast as subcases of our MDP formulation. Moreover, the approach offers flexibility to model users who are reactive to the quality of the received recommendations. In terms of performance, for users consuming an arbitrary number of contents in sequence, we show theoretically and using extensive validation over real traces that the MDP approach outperforms myopic algorithms both in session cost as well as in offered recommendation quality. Finally, even compared to optimal state-of-art algorithms targeting specific subcases, our MDP framework is significantly more efficient, speeding the execution time by a factor of 10, and enjoying better scaling with the content catalog and recommendation batch sizes.