Homo Silicus is Hyper-Rational: Why LLM Agents Fail to Replicate Attention-Driven Trading

Abstract excerpt

<title>Abstract</title> <p> Can large language model (LLM) agents serve as proxies for human investors in behavioral finance experiments? I deploy 96 GPT-4-family agents in a staggered difference-in-differences design, exposing treated agents to exogenous attention shocks and viral social media signals about meme stocks while holding the fundamentals constant. Whereas human retail investors substantially increas...

Topics

Open a Topic to create a Post that cites this publication.

• Machine Learning
• Models, Economic
• Phenotype

Identifiers and source

Literature Corpus work

f6ead9ac-4ed0-5ad4-a539-b80ade83386c

DOI

10.21203/rs.3.rs-9372266/v1