Enhancing E-Commerce Recommendation using Pre-Trained Language Model and Fine-Tuning

TL;DR

This paper explores integrating Pretrained Language Models with traditional recommendation algorithms to improve e-commerce recommendations by leveraging rich textual data, demonstrating enhanced predictive performance through domain-specific fine-tuning.

Contribution

It provides a comprehensive analysis of different strategies for incorporating PLMs into recommender systems and highlights the benefits of domain-specific fine-tuning in e-commerce.

Findings

PLMs improve recommendation accuracy over baseline models.

Domain-specific fine-tuning enhances model performance.

Textual information is crucial for effective e-commerce recommendations.

Abstract

Pretrained Language Models (PLM) have been greatly successful on a board range of natural language processing (NLP) tasks. However, it has just started being applied to the domain of recommendation systems. Traditional recommendation algorithms failed to incorporate the rich textual information in e-commerce datasets, which hinderss the performance of those models. We present a thorough investigation on the effect of various strategy of incorporating PLMs into traditional recommender algorithms on one of the e-commerce datasets, and we compare the results with vanilla recommender baseline models. We show that the application of PLMs and domain specific fine-tuning lead to an increase on the predictive capability of combined models. These results accentuate the importance of utilizing textual information in the context of e-commerce, and provides insight on how to better apply PLMs alongside traditional recommender system algorithms. The code used in this paper is available on Github: https://github.com/NuofanXu/bert_retail_recommender.