Large Language Model Driven User Cold Start Recommendations

Dalvi, Shubham Prabhakar (2025) Large Language Model Driven User Cold Start Recommendations. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (403kB) | Preview

Abstract

The advent of new and powerful LLM models has given rise to innovative approaches to using large language models and recommendation systems. These models have been trained on a large corpus of data and world knowledge, which can be harnessed in recommendation systems. The user cold start problem is a prominent obstacle in recommendation systems and businesses to retain initial users. This paper presents a novel approach to addressing the user cold-start problem, generating a user profile that can be utilized to provide recommendations for cold-start users. A comprehensive evaluation framework with 6 different approaches is used in this paper to evaluate the recommendation system.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Menghwar, Teerath Kumar UNSPECIFIED
Uncontrolled Keywords:	LLM(Large language models); Content Based Filtering; Collaborative Filtering; Cold Start Users; Prompting Techniques
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	01 Jul 2026 08:51
Last Modified:	01 Jul 2026 08:51
URI:	https://norma.ncirl.ie/id/eprint/9422

Actions (login required)

View Item