A hybrid stock prediction method based on periodic/non-periodic features analyses
Abstract Stock investment is an economic activity characterized by high risks and high returns. Therefore, the prediction of stock prices or fluctuations is of great importance to investors. Stock price prediction is a challenging task due to the nonlinearity and high volatility of stock time series...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | EPJ Data Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1140/epjds/s13688-024-00517-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559848571895808 |
|---|---|
| author | Cheng Zhao Junyi Cai Shuyi Yang |
| author_facet | Cheng Zhao Junyi Cai Shuyi Yang |
| author_sort | Cheng Zhao |
| collection | DOAJ |
| description | Abstract Stock investment is an economic activity characterized by high risks and high returns. Therefore, the prediction of stock prices or fluctuations is of great importance to investors. Stock price prediction is a challenging task due to the nonlinearity and high volatility of stock time series. Existing deep learning models may not capture the periodic and non-periodic features of stock data effectively. In this paper, we propose a novel model that leverages Complete Ensemble Empirical Mode Decomposition (CEEMD), Time2Vec, and Transformer to better capture and utilize various patterns in stock data for enhanced prediction performance, and we call it ETT. CEEMD decomposes the stock data into different frequency components based on their intrinsic scales. Time2Vec provides a time vector representation that captures both periodic and non-periodic patterns while being invariant to time scaling. Transformer learns the long-term dependencies and global information from the data. We apply ETT to predict stock prices in the Chinese A-share market and compare it with several baseline models. The results show that ETT reduces the mean squared error (MSE) by an average of 4% and increases the average cumulative return by 58% on the CSI 100 and Hushen 300 datasets. |
| format | Article |
| id | doaj-art-e009e8a93953450995688a05e9e358da |
| institution | Kabale University |
| issn | 2193-1127 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EPJ Data Science |
| spelling | doaj-art-e009e8a93953450995688a05e9e358da2025-01-05T12:11:21ZengSpringerOpenEPJ Data Science2193-11272025-01-0114111810.1140/epjds/s13688-024-00517-7A hybrid stock prediction method based on periodic/non-periodic features analysesCheng Zhao0Junyi Cai1Shuyi Yang2School of Economics, Zhejiang University of TechnologySchool of Computer Science, Zhejiang University of TechnologySchool of Computer Science, Zhejiang University of TechnologyAbstract Stock investment is an economic activity characterized by high risks and high returns. Therefore, the prediction of stock prices or fluctuations is of great importance to investors. Stock price prediction is a challenging task due to the nonlinearity and high volatility of stock time series. Existing deep learning models may not capture the periodic and non-periodic features of stock data effectively. In this paper, we propose a novel model that leverages Complete Ensemble Empirical Mode Decomposition (CEEMD), Time2Vec, and Transformer to better capture and utilize various patterns in stock data for enhanced prediction performance, and we call it ETT. CEEMD decomposes the stock data into different frequency components based on their intrinsic scales. Time2Vec provides a time vector representation that captures both periodic and non-periodic patterns while being invariant to time scaling. Transformer learns the long-term dependencies and global information from the data. We apply ETT to predict stock prices in the Chinese A-share market and compare it with several baseline models. The results show that ETT reduces the mean squared error (MSE) by an average of 4% and increases the average cumulative return by 58% on the CSI 100 and Hushen 300 datasets.https://doi.org/10.1140/epjds/s13688-024-00517-7CEEMDTime2VecTransformerPeriodic/Non-Periodic Features |
| spellingShingle | Cheng Zhao Junyi Cai Shuyi Yang A hybrid stock prediction method based on periodic/non-periodic features analyses EPJ Data Science CEEMD Time2Vec Transformer Periodic/Non-Periodic Features |
| title | A hybrid stock prediction method based on periodic/non-periodic features analyses |
| title_full | A hybrid stock prediction method based on periodic/non-periodic features analyses |
| title_fullStr | A hybrid stock prediction method based on periodic/non-periodic features analyses |
| title_full_unstemmed | A hybrid stock prediction method based on periodic/non-periodic features analyses |
| title_short | A hybrid stock prediction method based on periodic/non-periodic features analyses |
| title_sort | hybrid stock prediction method based on periodic non periodic features analyses |
| topic | CEEMD Time2Vec Transformer Periodic/Non-Periodic Features |
| url | https://doi.org/10.1140/epjds/s13688-024-00517-7 |
| work_keys_str_mv | AT chengzhao ahybridstockpredictionmethodbasedonperiodicnonperiodicfeaturesanalyses AT junyicai ahybridstockpredictionmethodbasedonperiodicnonperiodicfeaturesanalyses AT shuyiyang ahybridstockpredictionmethodbasedonperiodicnonperiodicfeaturesanalyses AT chengzhao hybridstockpredictionmethodbasedonperiodicnonperiodicfeaturesanalyses AT junyicai hybridstockpredictionmethodbasedonperiodicnonperiodicfeaturesanalyses AT shuyiyang hybridstockpredictionmethodbasedonperiodicnonperiodicfeaturesanalyses |