Effects of Using Synthetic Data on Deep Recommender Models' Performance

TL;DR

This paper explores how synthetic data generation can mitigate data imbalance issues in recommender systems, leading to improved performance by enhancing data diversity and reducing bias.

Contribution

It introduces and evaluates six synthetic data generation methods to improve recommender system accuracy under data imbalance conditions.

Findings

Synthetic negative samples improve AUC scores.

Data augmentation reduces bias towards popular items.

Synthetic data helps address data sparsity.

Abstract

Recommender systems are essential for enhancing user experiences by suggesting items based on individual preferences. However, these systems frequently face the challenge of data imbalance, characterized by a predominance of negative interactions over positive ones. This imbalance can result in biased recommendations favoring popular items. This study investigates the effectiveness of synthetic data generation in addressing data imbalances within recommender systems. Six different methods were used to generate synthetic data. Our experimental approach involved generating synthetic data using these methods and integrating the generated samples into the original dataset. Our results show that the inclusion of generated negative samples consistently improves the Area Under the Curve (AUC) scores. The significant impact of synthetic negative samples highlights the potential of data augmentation strategies to address issues of data sparsity and imbalance, ultimately leading to improved performance of recommender systems.