Shuaiyu Chen, T. Clifton Green, Huseyin Gulen, Dexin Zhou
{"title":"What Does ChatGPT Make of Historical Stock Returns? Extrapolation and Miscalibration in LLM Stock Return Forecasts","authors":"Shuaiyu Chen, T. Clifton Green, Huseyin Gulen, Dexin Zhou","doi":"arxiv-2409.11540","DOIUrl":null,"url":null,"abstract":"We examine how large language models (LLMs) interpret historical stock\nreturns and compare their forecasts with estimates from a crowd-sourced\nplatform for ranking stocks. While stock returns exhibit short-term reversals,\nLLM forecasts over-extrapolate, placing excessive weight on recent performance\nsimilar to humans. LLM forecasts appear optimistic relative to historical and\nfuture realized returns. When prompted for 80% confidence interval predictions,\nLLM responses are better calibrated than survey evidence but are pessimistic\nabout outliers, leading to skewed forecast distributions. The findings suggest\nLLMs manifest common behavioral biases when forecasting expected returns but\nare better at gauging risks than humans.","PeriodicalId":501273,"journal":{"name":"arXiv - ECON - General Economics","volume":"9 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - ECON - General Economics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11540","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
We examine how large language models (LLMs) interpret historical stock
returns and compare their forecasts with estimates from a crowd-sourced
platform for ranking stocks. While stock returns exhibit short-term reversals,
LLM forecasts over-extrapolate, placing excessive weight on recent performance
similar to humans. LLM forecasts appear optimistic relative to historical and
future realized returns. When prompted for 80% confidence interval predictions,
LLM responses are better calibrated than survey evidence but are pessimistic
about outliers, leading to skewed forecast distributions. The findings suggest
LLMs manifest common behavioral biases when forecasting expected returns but
are better at gauging risks than humans.