Optimizing Recommendations using Fine-Tuned LLMs

TL;DR

This paper introduces a method to improve media recommendations by generating synthetic datasets that enable users to express complex preferences naturally, enhancing personalization and the effectiveness of recommendation systems.

Contribution

It presents a novel approach to create synthetic datasets modeling real user interactions, supporting complex, expressive queries for improved recommendation accuracy.

Findings

Synthetic datasets improve diversity in training models

Enhanced personalization with complex user preferences

Better benchmarking of recommendation systems

Abstract

As digital media platforms strive to meet evolving user expectations, delivering highly personalized and intuitive movies and media recommendations has become essential for attracting and retaining audiences. Traditional systems often rely on keyword-based search and recommendation techniques, which limit users to specific keywords and a combination of keywords. This paper proposes an approach that generates synthetic datasets by modeling real-world user interactions, creating complex chat-style data reflective of diverse preferences. This allows users to express more information with complex preferences, such as mood, plot details, and thematic elements, in addition to conventional criteria like genre, title, and actor-based searches. In today's search space, users cannot write queries like ``Looking for a fantasy movie featuring dire wolves, ideally set in a harsh frozen world with themes of loyalty and survival.'' Building on these contributions, we evaluate synthetic datasets for diversity and effectiveness in training and benchmarking models, particularly in areas often absent from traditional datasets. This approach enhances personalization and accuracy by enabling expressive and natural user queries. It establishes a foundation for the next generation of conversational AI-driven search and recommendation systems in digital entertainment.