Hybrid preprocessing for neural network-based stock price prediction☆
Jian-Lei Li, Wei-Kang Shi · 2024
Read Hybrid preprocessing for neural network-based stock price prediction☆ by Jian-Lei Li, Wei-Kang Shi (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11665531.txt.
Description
Jian-Lei Li and Wei-Kang Shi propose a 2024 data prep method to help neural networks forecast stock prices. Price series have linked parts that move on fast and slow scales, which makes clean forecasts hard. Their method first splits the series into low and high parts with a wavelet method.
Warping measures then find parts that move alike across the series. High parts are cut into windows and shrunk with a standard method, while low parts are shrunk at once. The full prep raised forecast accuracy by about thirty percent over standard methods in their tests.
Catalog record
| CREATOR | Jian-Lei Li, Wei-Kang Shi |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |