Graph-Based Recommendation System

TL;DR

This paper introduces a graph-based recommendation system that leverages user space geometry to improve multi-armed bandit performance, reducing complexity while maintaining accuracy, validated through extensive simulations.

Contribution

It presents a novel graph-based approach for modeling user space in MAB recommendation systems, enhancing clustering and performance over existing methods.

Findings

Improved recommendation accuracy over state-of-the-art MAB algorithms.

Effect of graph sparsity and cluster size on system performance analyzed.

Validated results on both synthetic and real datasets.

Abstract

In this work, we study recommendation systems modelled as contextual multi-armed bandit (MAB) problems. We propose a graph-based recommendation system that learns and exploits the geometry of the user space to create meaningful clusters in the user domain. This reduces the dimensionality of the recommendation problem while preserving the accuracy of MAB. We then study the effect of graph sparsity and clusters size on the MAB performance and provide exhaustive simulation results both in synthetic and in real-case datasets. Simulation results show improvements with respect to state-of-the-art MAB algorithms.