LLM-Enhanced Reranking for Complementary Product Recommendation

TL;DR

This paper proposes a model-agnostic LLM-based reranking method to improve the accuracy and diversity of complementary product recommendations in e-commerce, without retraining existing models.

Contribution

It introduces a novel LLM prompting strategy for reranking that enhances recommendation quality and diversity, addressing limitations of prior GNN-based approaches.

Findings

50% increase in accuracy metrics

2% increase in diversity metrics

Effective on multiple public datasets

Abstract

Complementary product recommendation, which aims to suggest items that are used together to enhance customer value, is a crucial yet challenging task in e-commerce. While existing graph neural network (GNN) approaches have made significant progress in capturing complex product relationships, they often struggle with the accuracy-diversity tradeoff, particularly for long-tail items. This paper introduces a model-agnostic approach that leverages Large Language Models (LLMs) to enhance the reranking of complementary product recommendations. Unlike previous works that use LLMs primarily for data preprocessing and graph augmentation, our method applies LLM-based prompting strategies directly to rerank candidate items retrieved from existing recommendation models, eliminating the need for model retraining. Through extensive experiments on public datasets, we demonstrate that our approach effectively balances accuracy and diversity in complementary product recommendations, with at least 50% lift in accuracy metrics and 2% lift in diversity metrics on average for the top recommended items across datasets.