Revealing the Unobserved by Linking Collaborative Behavior and Side Knowledge

TL;DR

This paper introduces a tensor-based hybrid recommendation model that integrates granular user preferences with side information, addressing data sparsity and capturing user intent more effectively.

Contribution

It presents a novel tensor model that directly links side information with collaborative data, improving recommendation accuracy and handling diverse interaction types.

Findings

Effective on multiple benchmark datasets

Addresses data sparsity issues

Flexible for various interaction types

Abstract

We propose a tensor-based model that fuses a more granular representation of user preferences with the ability to take additional side information into account. The model relies on the concept of ordinal nature of utility, which better corresponds to actual user perception. In addition to that, unlike the majority of hybrid recommenders, the model ties side information directly to collaborative data, which not only addresses the problem of extreme data sparsity, but also allows to naturally exploit patterns in the observed behavior for a more meaningful representation of user intents. We demonstrate the effectiveness of the proposed model on several standard benchmark datasets. The general formulation of the approach imposes no restrictions on the type of observed interactions and makes it potentially applicable for joint modelling of context information along with side data.