Investor risk profiles of large language models

TL;DR

This study evaluates how large language models simulate investor risk profiles, revealing differences in risk tolerance and the influence of personas, which has implications for AI-driven financial advising.

Contribution

It systematically compares LLMs' risk profiles and shows how personas affect their investment risk assessments, a novel analysis in AI financial modeling.

Findings

Gemini has a moderate, consistent risk profile

Llama is more conservative in risk tolerance

GPT shows moderate aggressiveness with high response variability

Abstract

This paper investigates how large language models (LLMs) form and express investor risk profiles, a critical component of retail investment advising. We examine three LLMs (GPT, Gemini, and Llama) and assess their responses to a standardized risk questionnaire under varying prompts. In particular, we establish each model's default investment profile by analyzing repeated responses per model. We observe that LLMs are generally longterm investors but exhibit different tendencies in risk tolerance: Gemini has a moderate risk level with highly consistent responses, Llama skews more conservative, and GPT appears moderately aggressive with the greatest variation in answers. Moreover, we find that assigning specific personas such as age, wealth, and investment experience leads each LLM to adjust its risk profile, although the extent of these adjustments differs across the models.