Study on Exchange Rate Forecasting with Stacked Optimization Based on a Learning Algorithm
The time series of exchange rate fluctuations are characterized by non-stationary and nonlinear features, and forecasting using traditional linear or single-machine models can cause significant bias. Based on this, the authors propose the combination of the advantages of the EMD and LSTM models to r...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/4/614 |
| _version_ | 1797297516142657536 |
|---|---|
| author | Weiwei Xie Haifeng Wu Boyu Liu Shengdong Mu Nedjah Nadia |
| author_facet | Weiwei Xie Haifeng Wu Boyu Liu Shengdong Mu Nedjah Nadia |
| author_sort | Weiwei Xie |
| collection | DOAJ |
| description | The time series of exchange rate fluctuations are characterized by non-stationary and nonlinear features, and forecasting using traditional linear or single-machine models can cause significant bias. Based on this, the authors propose the combination of the advantages of the EMD and LSTM models to reduce the complexity by analyzing and decomposing the time series and forming a new model, EMD-LSTM-SVR, with a stronger generalization ability. More than 30,000 units of data on the USD/CNY exchange rate opening price from 2 January 2015 to 30 April 2022 were selected for an empirical demonstration of the model’s accuracy. The empirical results showed that the prediction of the exchange rate fluctuation with the EMD-LSTM-SVR model not only had higher accuracy, but also ensured that most of the predicted positions deviated less from the actual positions. The new model had a stronger generalization ability, a concise structure, and a high degree of ability to fit nonlinear features, and it prevented gradient vanishing and overfitting to achieve a higher degree of prediction accuracy. |
| first_indexed | 2024-03-07T22:22:26Z |
| format | Article |
| id | doaj.art-06c194eeed4b44e0a76bbd89bfc280ae |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-07T22:22:26Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-06c194eeed4b44e0a76bbd89bfc280ae2024-02-23T15:26:18ZengMDPI AGMathematics2227-73902024-02-0112461410.3390/math12040614Study on Exchange Rate Forecasting with Stacked Optimization Based on a Learning AlgorithmWeiwei Xie0Haifeng Wu1Boyu Liu2Shengdong Mu3Nedjah Nadia4School of Public Administration, Central China Normal University, Wuhan 430079, ChinaSustainable Finance Research Center, Shenzhen Institute of Data Economy Research Fellow of Shenzhen Finance Institute, Shenzhen 518172, ChinaSchool of Innovation and Entrepreneurship, Hubei University of Economics, Wuhan 430205, ChinaCollaborative Innovation Center of Green Development in the Wuling Shan Region, Yangtze Normal University, Fuling, Chongqing 408100, ChinaDepartment of Electronics Engineering and Telecommunications, State University of Rio de Janeiro, Rio de Janeiro 205513, BrazilThe time series of exchange rate fluctuations are characterized by non-stationary and nonlinear features, and forecasting using traditional linear or single-machine models can cause significant bias. Based on this, the authors propose the combination of the advantages of the EMD and LSTM models to reduce the complexity by analyzing and decomposing the time series and forming a new model, EMD-LSTM-SVR, with a stronger generalization ability. More than 30,000 units of data on the USD/CNY exchange rate opening price from 2 January 2015 to 30 April 2022 were selected for an empirical demonstration of the model’s accuracy. The empirical results showed that the prediction of the exchange rate fluctuation with the EMD-LSTM-SVR model not only had higher accuracy, but also ensured that most of the predicted positions deviated less from the actual positions. The new model had a stronger generalization ability, a concise structure, and a high degree of ability to fit nonlinear features, and it prevented gradient vanishing and overfitting to achieve a higher degree of prediction accuracy.https://www.mdpi.com/2227-7390/12/4/614LSTMEMDoptimizationexchange rate prediction |
| spellingShingle | Weiwei Xie Haifeng Wu Boyu Liu Shengdong Mu Nedjah Nadia Study on Exchange Rate Forecasting with Stacked Optimization Based on a Learning Algorithm Mathematics LSTM EMD optimization exchange rate prediction |
| title | Study on Exchange Rate Forecasting with Stacked Optimization Based on a Learning Algorithm |
| title_full | Study on Exchange Rate Forecasting with Stacked Optimization Based on a Learning Algorithm |
| title_fullStr | Study on Exchange Rate Forecasting with Stacked Optimization Based on a Learning Algorithm |
| title_full_unstemmed | Study on Exchange Rate Forecasting with Stacked Optimization Based on a Learning Algorithm |
| title_short | Study on Exchange Rate Forecasting with Stacked Optimization Based on a Learning Algorithm |
| title_sort | study on exchange rate forecasting with stacked optimization based on a learning algorithm |
| topic | LSTM EMD optimization exchange rate prediction |
| url | https://www.mdpi.com/2227-7390/12/4/614 |
| work_keys_str_mv | AT weiweixie studyonexchangerateforecastingwithstackedoptimizationbasedonalearningalgorithm AT haifengwu studyonexchangerateforecastingwithstackedoptimizationbasedonalearningalgorithm AT boyuliu studyonexchangerateforecastingwithstackedoptimizationbasedonalearningalgorithm AT shengdongmu studyonexchangerateforecastingwithstackedoptimizationbasedonalearningalgorithm AT nedjahnadia studyonexchangerateforecastingwithstackedoptimizationbasedonalearningalgorithm |