What Does ChatGPT Make of Historical Stock Returns? Extrapolation and Miscalibration in LLM Stock Return Forecasts

Abstract

We examine how large language models (LLMs) interpret historical stock returns and price charts when prompted to forecast returns over short horizons. While stock returns exhibit short-term reversals, LLM forecasts over-extrapolate, placing excessive weight on recent performance. Simulations indicate that LLM extrapolation is stronger for less persistent series, similar to humans, and difficult to eliminate through prompt engineering. LLM forecasts also appear optimistic relative to historical and future returns. When prompted for 80% confidence interval predictions, LLM forecasts are better calibrated than survey evidence. The findings suggest LLMs manifest common behavioral biases but are better at gauging risks than humans.

Keywords: Large language models, Generative AI, Return forecasts, Extrapolative expectations

JEL Classification: D84, G17, G40, O33