生成式智能体与预期:大语言模型(LLM)是否与异质主体模型(HAM)一致?
Generative Agents and Expectations: Do LLMs Align with Heterogeneous Agent Models?
AI总结:
本文利用大语言模型构建生成式智能体以确定金融市场中基本面分析者和趋势追随者的策略采用概率,并将其与1990-2020年S&P 500指数的异质主体模型(HAM)文献结果对比,发现AI预期与HAM一致,且人工市场数据揭示了预期异质性及向基本面分析者行为的系统性不对称。
摘要:
异质主体模型(HAM)文献中的研究结果确定了金融市场中基本面分析者和趋势追随者的比例,该比例会根据所分析的时期而变化。本文中,我们使用大语言模型(LLM)构建一个生成式智能体(GA),该智能体基于当前信息确定采用两种策略之一的概率。我们将策略采用概率与HAM文献中1990年至2020年标准普尔500指数(S&P 500)的相关概率进行了比较。研究结果表明,由此产生的人工智能(AI)预期与HAM文献中报告的预期一致。同时,将分析扩展到人工市场数据有助于我们筛选AI智能体的决策过程。在人工市场中,结果证实了预期的异质性,但揭示了其向基本面分析者行为的系统性不对称。
英文摘要:
Results in the Heterogeneous Agent Model (HAM) literature determine the proportion of fundamentalists and trend followers in the financial market. This proportion varies according to the periods analyzed. In this paper, we use a large language model (LLM) to construct a generative agent (GA) that determines the probability of adopting one of the two strategies based on current information. The probabilities of strategy adoption are compared with those in the HAM literature for the S\&P 500 index between 1990 and 2020. Our findings suggest that the resulting artificial intelligence (AI) expectations align with those reported in the HAM literature. At the same time, extending the analysis to artificial market data helps us to filter the decision-making process of the AI agent. In the artificial market, results confirm the heterogeneity in expectations but reveal systematic asymmetry toward the fundamentalist behavior.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。