StockGPT: A GenAI Model for Stock Prediction and Trading

19 Pages Posted: 19 Apr 2024

See all articles by Dat Mai

Dat Mai

University of Missouri at Columbia

Date Written: April 7, 2024

Abstract

This paper introduces StockGPT, an autoregressive ``number'' model trained and tested on 70 million daily U.S. stock returns over nearly 100 years. Treating each return series as a sequence of tokens, StockGPT automatically learns the hidden patterns predictive of future returns via its attention mechanism. On a held-out test sample from 2001 to 2023, a daily rebalanced long-short portfolio formed from StockGPT predictions earns an annual return of 119% with a Sharpe ratio of 6.5. The StockGPT-based portfolio completely spans momentum and long-/short-term reversals, eliminating the need for manually crafted price-based strategies, and also encompasses most leading stock market factors. This highlights the immense promise of generative AI in surpassing human in making complex financial investment decisions.

Keywords: generative artificial intelligence, transformer, decoder, stock market, investment, trading, return prediction

JEL Classification: G00, G10, G11, G12, C00, C01, C02

Suggested Citation

Mai, Dat, StockGPT: A GenAI Model for Stock Prediction and Trading (April 7, 2024). Available at SSRN: https://ssrn.com/abstract=4787199 or http://dx.doi.org/10.2139/ssrn.4787199

Dat Mai (Contact Author)

University of Missouri at Columbia ( email )

Columbia, MO 65201
United States

HOME PAGE: http://www.maiydat.com/

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
202
Abstract Views
572
Rank
278,155
PlumX Metrics