Hierarchical Organization Simulacra in the Investment Sector

TL;DR

This study uses multi-agent simulation to mimic hierarchical decision-making in investment firms, demonstrating that such models can closely replicate professional trader behavior and profitability, while also revealing biases influenced by language and perceived authority.

Contribution

Introduces a hierarchical multi-agent simulation approach for modeling investment decision-making, highlighting its alignment with professional traders and exposing decision biases.

Findings

Simulation closely matches professional trader decisions in frequency and profitability

Language and perceived seniority significantly influence decision outcomes

Large language models can replicate aspects of professional financial behavior

Abstract

This paper explores designing artificial organizations with professional behavior in investments using a multi-agent simulation. The method mimics hierarchical decision-making in investment firms, using news articles to inform decisions. A large-scale study analyzing over 115,000 news articles of 300 companies across 15 years compared this approach against professional traders' decisions. Results show that hierarchical simulations align closely with professional choices, both in frequency and profitability. However, the study also reveals biases in decision-making, where changes in prompt wording and perceived agent seniority significantly influence outcomes. This highlights both the potential and limitations of large language models in replicating professional financial decision-making.