A Comparative Analysis of Portfolio Construction Using LLM-Based Investment Models and Modern Portfolio Theory for Financially Inexperienced Users

Blanco Araujo, Martha Abril (2025) A Comparative Analysis of Portfolio Construction Using LLM-Based Investment Models and Modern Portfolio Theory for Financially Inexperienced Users. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The investment landscape is changing with the rise of artificial intelligence tools, especially Large Language Models (LLMs) like ChatGPT, which aim to make financial investing more accessible. Yet, investors with little or no experience often face challenges building balanced portfolios, mainly due to limited knowledge of risk management and diversification. While Modern Portfolio Theory (MPT) has long been the standard, conversational AI is emerging as a simpler entry point for beginners.

This study compared portfolios built using a simple prompt, a technical prompt, and a Human approach using MPT, all portfolios were tested over the same period of time. Portfolios from simple prompts delivered strong results but came with high volatility and poor diversification, making them risky for novice investors. Technical prompts produced more stable outcomes, and MPT offered the lowest volatility overall. These findings suggest that LLM-based tools can help new investors if used with technical guidance and proper risk controls, while simple prompts may encourage risk-taking beyond a safe tolerance, underlining the need for built-in safeguards.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Cosgrave, Noel UNSPECIFIED
Subjects:	H Social Sciences > HG Finance 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 P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing H Social Sciences > HG Finance > Fintech T Technology > T Technology (General) > Information Technology > Fintech
Divisions:	School of Computing > Master of Science in FinTech
Depositing User:	Ciara O'Brien
Date Deposited:	24 Jun 2026 10:23
Last Modified:	24 Jun 2026 10:23
URI:	https://norma.ncirl.ie/id/eprint/9390

Actions (login required)

View Item