Supervised autoencoder MLP for financial time series forecasting
Uložené v:
| Názov: | Supervised autoencoder MLP for financial time series forecasting |
|---|---|
| Autori: | Bartosz Bieganowski, Robert Ślepaczuk |
| Zdroj: | Journal of Big Data, Vol 12, Iss 1, Pp 1-45 (2025) |
| Informácie o vydavateľovi: | SpringerOpen, 2025. |
| Rok vydania: | 2025 |
| Zbierka: | LCC:Computer engineering. Computer hardware LCC:Information technology LCC:Electronic computers. Computer science |
| Predmety: | Machine learning, Algorithmic investment strategy, Supervised autoencoders, Financial time series, Trading strategy, Risk-adjusted return, Computer engineering. Computer hardware, TK7885-7895, Information technology, T58.5-58.64, Electronic computers. Computer science, QA75.5-76.95 |
| Popis: | Abstract This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders, aiming to improve investment strategy performance. It specifically examines the impact of noise augmentation and triple barrier labeling on risk-adjusted returns, using the Sharpe and Information Ratios. The study focuses on the S&P 500 index, EUR/USD, and BTC/USD as the traded assets from January 1, 2016, to April 30, 2022. Findings indicate that supervised autoencoders, with balanced noise augmentation and bottleneck size, significantly boost strategy effectiveness. However, excessive noise and large bottleneck sizes can impair performance, highlighting the importance of precise parameter tuning. This paper also presents a derivation of a novel optimization metric that can be used with triple barrier labeling. The results of this study have substantial policy implications, suggesting that financial institutions and regulators could leverage techniques presented to enhance market stability and investor protection, while also encouraging more informed and strategic investment approaches in various financial sectors. |
| Druh dokumentu: | article |
| Popis súboru: | electronic resource |
| Jazyk: | English |
| ISSN: | 2196-1115 |
| Relation: | https://doaj.org/toc/2196-1115 |
| DOI: | 10.1186/s40537-025-01267-7 |
| Prístupová URL adresa: | https://doaj.org/article/92f2bc1809ae4a7e9a1c04edd5b701dc |
| Prístupové číslo: | edsdoj.92f2bc1809ae4a7e9a1c04edd5b701dc |
| Databáza: | Directory of Open Access Journals |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | Abstract This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders, aiming to improve investment strategy performance. It specifically examines the impact of noise augmentation and triple barrier labeling on risk-adjusted returns, using the Sharpe and Information Ratios. The study focuses on the S&P 500 index, EUR/USD, and BTC/USD as the traded assets from January 1, 2016, to April 30, 2022. Findings indicate that supervised autoencoders, with balanced noise augmentation and bottleneck size, significantly boost strategy effectiveness. However, excessive noise and large bottleneck sizes can impair performance, highlighting the importance of precise parameter tuning. This paper also presents a derivation of a novel optimization metric that can be used with triple barrier labeling. The results of this study have substantial policy implications, suggesting that financial institutions and regulators could leverage techniques presented to enhance market stability and investor protection, while also encouraging more informed and strategic investment approaches in various financial sectors. |
|---|---|
| ISSN: | 21961115 |
| DOI: | 10.1186/s40537-025-01267-7 |