PulseAugur
EN
LIVE 07:48:16

LLMs struggle to simulate complex financial trading behavior

By PulseAugur Editorial · [1 sources] ·

A preliminary study investigated the effectiveness of large language models (LLMs) in simulating individual financial trading decisions. In a controlled paper-trading environment with 120 volunteers, LLMs were used to predict participants' actions, traded securities, and transaction quantities based on pre-cutoff information. While market context improved prediction accuracy for actions and tickers, transaction sizing remained challenging. The study also identified systematic behavioral compression in LLMs, including overproduction of hold actions and underprediction of sell decisions. AI

IMPACT This research highlights limitations in LLMs' ability to accurately model complex human financial decision-making, suggesting current models may not be suitable for sophisticated financial simulation tasks.

RANK_REASON Academic paper published on arXiv detailing a study. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

LLMs struggle to simulate complex financial trading behavior

How we ranked this

Signal score
20 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Academic paper published on arXiv detailing a study. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Jiajie He, Jiangyuan Hong, Dongling Ni, Wenjin Liu, Xintong Chen ·

    Are LLMs Good Financial User Simulators? A Preliminary Study

    arXiv:2609.15727v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as user simulators, but their ability to reproduce evolving individual financial decisions remains unclear. We present a preliminary study in a controlled paper-trading environment …

RELATED ENTITIES

RELATED TOPICS