StockGPT: A GenAI Model for Stock Prediction and Trading
This addresses stock market prediction for investors, offering a novel AI-driven approach that automates strategies and shows strong performance, though it is incremental in applying existing AI methods to finance.
The paper tackles stock prediction by introducing StockGPT, a generative AI model trained on 70 million daily U.S. stock returns over nearly 100 years, which yields highly significant alphas against leading market factors in test portfolios from 2001 to 2023.
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, daily and monthly rebalanced long-short portfolios formed from StockGPT predictions yield strong performance. The StockGPT-based portfolios span momentum and long-/short-term reversals, eliminating the need for manually crafted price-based strategies, and yield highly significant alphas against leading stock market factors, suggesting a novel AI pricing effect. This highlights the immense promise of generative AI in surpassing human in making complex financial investment decisions.