Neural Hybrid Recommender: Recommendation needs collaboration

TL;DR

This paper introduces NHR, a flexible neural network framework for recommender systems that integrates diverse data sources, demonstrating superior performance on benchmark and real-world datasets.

Contribution

The paper presents a generalized, extendable neural network framework for recommender systems that can incorporate multiple data sources and improve prediction accuracy.

Findings

NHR outperforms state-of-the-art methods on benchmark datasets.

The framework is adaptable for both item and rating prediction tasks.

Experimental results confirm the effectiveness of the proposed approach.

Abstract

In recent years, deep learning has gained an indisputable success in computer vision, speech recognition, and natural language processing. After its rising success on these challenging areas, it has been studied on recommender systems as well, but mostly to include content features into traditional methods. In this paper, we introduce a generalized neural network-based recommender framework that is easily extendable by additional networks. This framework named NHR, short for Neural Hybrid Recommender allows us to include more elaborate information from the same and different data sources. We have worked on item prediction problems, but the framework can be used for rating prediction problems as well with a single change on the loss function. To evaluate the effect of such a framework, we have tested our approach on benchmark and not yet experimented datasets. The results in these real-world datasets show the superior performance of our approach in comparison with the state-of-the-art methods.