数据与计算发展前沿2026，Vol.8Issue(1)：2-13,12.DOI:10.11871/jfdc.issn.2096-742X.2026.01.001
大语言模型驱动的市场交易行为模拟
Market Trading Behavior Simulation Driven by Large Language Models
摘要
Abstract
[Objective]In markets,participants'decisions are reflected through market trading.Under-standing market trading is crucial for grasping the operational mechanisms of markets.This pa-per aims to assess whether Large Language Models(LLMs)can replicate bounded rationality in human market trading decisions and to explore the potential and limitations of LLMs in mar-ket trading simulation.[Methods]Behavioral economics theories,such as framing effect,en-dowment effect,and mental accounting,highlight how cognitive biases,emotional factors,and external information influence human market trading decisions.These theories form the basis for understanding bounded rationality in human decision-making.Building on these classic theories,this paper designs and imple-ments four types of experiments:a questionnaire simulation,a fair price simulation,a voucher exchange simula-tion,and a product trading simulation.This study evaluates the human-like consistency of LLMs by analyzing the alignment between LLMs'responses and human decisions in the questionnaire experiments and their trading deci-sions in the exchange experiments.[Results]The experimental results show that LLMs align closely with hu-mans in the questionnaire experiments.Factors such as persona,phrasing of questions,and the sequence of event descriptions significantly influence LLMs'decisions.However,LLMs differ from humans in pricing decisions and value assessments and fail to reproduce key behavioral patterns implied by mental accounting and the endow-ment effect.[Conclusions]In conclusion,while LLMs can simulate human market trading decisions in specific contexts,they still face limitations in fully replicating bounded rationality in human decision-making.关键词
市场交易/大语言模型/行为经济学/有限理性/模拟能力Key words
market trading/Large Language Models(LLMs)/behavioral economics/bounded rationality/simulation capability引用本文复制引用
王成,曾诗容,王楚文,蒋昌俊..大语言模型驱动的市场交易行为模拟[J].数据与计算发展前沿,2026,8(1):2-13,12.基金项目
国家自然科学基金(62372328,72342026) （62372328,72342026）
