----------------------------------------------------------------------------------------------------

         Department of Systems Engineering and Engineering Management

                             The Chinese University of Hong Kong

----------------------------------------------------------------------------------------------------



Date: 2:00pm - 3:00pm on 7 November (Friday)

Venue: ERB 513, The Chinese University of Hong Kong

Title: LLMs for Portfolio Selection

Speaker: Yongjae Lee, Department of Industrial Engineering and

Artificial Intelligence Graduate School, Ulsan National Institute of

Science and Technology



Abstract:

Large Language Models (LLMs) are reshaping the landscape of investment

decision-making with their capacity for large-scale textual analysis and

reasoning. However, concerns about hallucination and reliability

continue to limit their direct application in high-stakes financial

settings. This talk aims to address, from multiple perspectives, the

various considerations and cautions that must be taken into account when

integrating LLMs into the portfolio selection process. We explore three

aspects: (1) identifying and analyzing biases in LLMs within investment

contexts such as sector, size, or momentum preferences, (2) fine-tuning

LLM embedding models to align with investment themes of financial

assets, and (3) incorporating LLM-generated views into portfolio

optimization using the Black-Litterman model. Together, these components

offer a practical roadmap for utilizing LLMs in investment workflows,

balancing innovation with risk awareness.



links to papers:

https://arxiv.org/abs/2507.20957

https://arxiv.org/abs/2508.16936

https://arxiv.org/abs/2504.14345



Biography:

Yongjae Lee is an Associate Professor in the Department of Industrial

Engineering and Artificial Intelligence Graduate School at Ulsan

National Institute of Science and Technology (UNIST). Dr. Lee utilizes

quantitative techniques such as ML/AI and optimization to analyze

financial data and derive optimal decisions. He is particularly

interested in analyzing individual and household financial activities to

draw useful insights and design customized services. He is an advisory

editorial board member for the Journal of Financial Data Science and

served as an organizing committee member(workshop chair) of ICAIF'24. He

has applied ML/AI techniques to develop financial services through

projects with several financial and IT companies and government

agencies. Dr. Lee is an advisor professor of LinqAlpha and a member of

AI in Finance Committee of Financial Services Commission of Korea. He

received his B.S. degree in computer science and mathematical sciences

and Ph.D. degree in industrial and systems engineering from KAIST.