StockGPT: A GenAI Model for Stock Prediction and Trading
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929554702991360 |
|---|---|
| author | Mai, Dat |
| author_facet | Mai, Dat |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05101 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | StockGPT: A GenAI Model for Stock Prediction and Trading Mai, Dat Computational Finance Artificial Intelligence Portfolio Management Pricing of Securities Statistical Finance 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. |
| title | StockGPT: A GenAI Model for Stock Prediction and Trading |
| topic | Computational Finance Artificial Intelligence Portfolio Management Pricing of Securities Statistical Finance |
| url | https://arxiv.org/abs/2404.05101 |