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

ArXiv ID: 2411.05801 “View on arXiv”

Authors: Unknown

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.

Keywords: Large Language Models, Big Five Personality, Investment Behavior, Risk Appetite, Simulation, Equities

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Street Traders
• Why: The paper applies established statistical methods (OLS regression) and standard personality models (Big Five) with moderate complexity, but its primary contribution is a simulation-based empirical study comparing LLM personas to human behavior in an investment task, involving specific data collection and implementation steps.

  flowchart TD
    A["Research Goal<br>Do LLM Personas mirror human investment behavior<br>based on Five-Factor Model traits?"] --> B

    subgraph B ["Methodology & Data"]
        direction LR
        B1["Big Five<br>Personality Profiles"] --> B2["Investment Task<br>Simulated Environment"]
        B3["Human Baseline<br>Survey Data"] --> B2
    end

    B --> C["Computational Process<br>LLM Simulation & Comparative Analysis"]

    C --> D{"Outcome 1: Behavioral Consistency"}
    C --> E{"Outcome 2: Domain Generalization"}
    C --> F{"Outcome 3: Context Sensitivity"}

    D --> D1["LLM personas exhibited meaningful<br>behavioral differences across categories"]
    E --> E1["Accurate representation in:<br>Learning Style, Impulsivity, Risk Appetite"]
    E --> E2["Failed representation in:<br>Environmental Attitudes"]
    F --> F1["Simulation behavior more reflective<br>of human behavior vs. Survey"]

    style A fill:#e1f5fe
    style B fill:#fff3e0
    style C fill:#f3e5f5
    style D fill:#e8f5e8
    style E fill:#e8f5e8
    style F fill:#e8f5e8