Do LLM Personas Dream of Bull Markets? Comparing Human and AI Investment Strategies Through the Lens of the Five-Factor Model

TL;DR

This study explores whether Large Language Models with specific personality profiles can mimic human investment behaviors, revealing that LLMs exhibit trait-consistent behaviors in some areas but not all, especially in environmental attitudes.

Contribution

It demonstrates that LLMs can generalize personality traits into investment behaviors, aligning with human patterns in a simulated environment, and compares their performance to human data.

Findings

LLMs show trait-consistent behaviors in learning, impulsivity, and risk appetite.

Environmental attitudes are not accurately represented by LLMs.

LLMs behave more like humans in simulation than in surveys.

Abstract

Large Language Models (LLMs) have demonstrated the ability to adopt a personality and behave in a human-like manner. There is a large body of research that investigates the behavioural impacts of personality in less obvious areas such as investment attitudes or creative decision making. In this study, we investigated whether an LLM persona with a specific Big Five personality profile would perform an investment task similarly to a human with the same personality traits. We used a simulated investment task to determine if these results could be generalised into actual behaviours. In this simulated environment, our results show these personas produced meaningful behavioural differences in all assessed categories, with these behaviours generally being consistent with expectations derived from human research. We found that LLMs are able to generalise traits into expected behaviours in three areas: learning style, impulsivity and risk appetite while environmental attitudes could not be accurately represented. In addition, we showed that LLMs produce behaviour that is more reflective of human behaviour in a simulation environment compared to a survey environment.