LLMRS: Unlocking Potentials of LLM-Based Recommender Systems for Software Purchase

TL;DR

This paper introduces LLMRS, a zero-shot recommender system leveraging large language models to analyze user reviews, which outperforms traditional models in software purchase recommendations by capturing meaningful review information.

Contribution

The paper presents LLMRS, a novel zero-shot LLM-based recommender system that effectively encodes user reviews for improved software purchase suggestions.

Findings

LLMRS outperforms baseline ranking models.

It captures meaningful information from reviews.

Provides more reliable recommendations.

Abstract

Recommendation systems are ubiquitous, from Spotify playlist suggestions to Amazon product suggestions. Nevertheless, depending on the methodology or the dataset, these systems typically fail to capture user preferences and generate general recommendations. Recent advancements in Large Language Models (LLM) offer promising results for analyzing user queries. However, employing these models to capture user preferences and efficiency remains an open question. In this paper, we propose LLMRS, an LLM-based zero-shot recommender system where we employ pre-trained LLM to encode user reviews into a review score and generate user-tailored recommendations. We experimented with LLMRS on a real-world dataset, the Amazon product reviews, for software purchase use cases. The results show that LLMRS outperforms the ranking-based baseline model while successfully capturing meaningful information from product reviews, thereby providing more reliable recommendations.