Enhanced foreign exchange volatility forecasting using CEEMDAN with optuna-optimized ensemble deep learning model
Foreign Exchange (FX) is the largest financial market in the world, with a daily trading volume that significantly exceeds that of stock and futures markets. The prediction of FX volatility is a critical financial concern that has garnered significant attention from researchers and practitioners due...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2024
|
| Online Access: | http://journalarticle.ukm.my/24507/ http://journalarticle.ukm.my/24507/1/SS%2025.pdf |
| _version_ | 1848816121531072512 |
|---|---|
| author | Kausar, Rehan Iqbal, Farhat Raziq, Abdul Sheikh, Naveed Rehman, Abdul |
| author_facet | Kausar, Rehan Iqbal, Farhat Raziq, Abdul Sheikh, Naveed Rehman, Abdul |
| author_sort | Kausar, Rehan |
| building | UKM Institutional Repository |
| collection | Online Access |
| description | Foreign Exchange (FX) is the largest financial market in the world, with a daily trading volume that significantly exceeds that of stock and futures markets. The prediction of FX volatility is a critical financial concern that has garnered significant attention from researchers and practitioners due to its far-reaching implications in the financial markets. This paper presents a novel hybrid ensemble forecasting model integrating a decomposition strategy and three deep learning (DL) models: Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Convolutional Neural Network (CNN). This combination addresses individual models’ limitations and further improves the accuracy and stability of FX volatility forecasting. The proposed approach utilizes the CEEMDAN technique to decompose volatility into multiple distinct intrinsic mode functions (IMFs) and merges these IMFs with GARCH and EGARCH volatilities to form the input dataset for the DL models. In addition, we employed an attention mechanism to improve the effectiveness of the DL techniques. Furthermore, the hyperparameters for the DL models are optimized using the Optuna algorithm. Finally, a hybrid ensemble model for forecasting exchange rate volatility is developed by combining the predictions of three distinct DL models. The proposed approach is evaluated against various benchmark models using evaluation measures such as MSE, MAE, HMSE, HMAE, RMSE, Q-LIKE, and the model confidence set (MCS) approach. The results demonstrate that our proposed approach provides accurate and reliable forecasts of FX volatility under different forecasting regimes, making it a valuable tool for financial practitioners and researchers. |
| first_indexed | 2025-11-15T01:00:50Z |
| format | Article |
| id | oai:generic.eprints.org:24507 |
| institution | Universiti Kebangasaan Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T01:00:50Z |
| publishDate | 2024 |
| publisher | Penerbit Universiti Kebangsaan Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | oai:generic.eprints.org:245072024-11-12T07:34:22Z http://journalarticle.ukm.my/24507/ Enhanced foreign exchange volatility forecasting using CEEMDAN with optuna-optimized ensemble deep learning model Kausar, Rehan Iqbal, Farhat Raziq, Abdul Sheikh, Naveed Rehman, Abdul Foreign Exchange (FX) is the largest financial market in the world, with a daily trading volume that significantly exceeds that of stock and futures markets. The prediction of FX volatility is a critical financial concern that has garnered significant attention from researchers and practitioners due to its far-reaching implications in the financial markets. This paper presents a novel hybrid ensemble forecasting model integrating a decomposition strategy and three deep learning (DL) models: Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Convolutional Neural Network (CNN). This combination addresses individual models’ limitations and further improves the accuracy and stability of FX volatility forecasting. The proposed approach utilizes the CEEMDAN technique to decompose volatility into multiple distinct intrinsic mode functions (IMFs) and merges these IMFs with GARCH and EGARCH volatilities to form the input dataset for the DL models. In addition, we employed an attention mechanism to improve the effectiveness of the DL techniques. Furthermore, the hyperparameters for the DL models are optimized using the Optuna algorithm. Finally, a hybrid ensemble model for forecasting exchange rate volatility is developed by combining the predictions of three distinct DL models. The proposed approach is evaluated against various benchmark models using evaluation measures such as MSE, MAE, HMSE, HMAE, RMSE, Q-LIKE, and the model confidence set (MCS) approach. The results demonstrate that our proposed approach provides accurate and reliable forecasts of FX volatility under different forecasting regimes, making it a valuable tool for financial practitioners and researchers. Penerbit Universiti Kebangsaan Malaysia 2024 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/24507/1/SS%2025.pdf Kausar, Rehan and Iqbal, Farhat and Raziq, Abdul and Sheikh, Naveed and Rehman, Abdul (2024) Enhanced foreign exchange volatility forecasting using CEEMDAN with optuna-optimized ensemble deep learning model. Sains Malaysiana, 53 (9). pp. 3229-3239. ISSN 0126-6039 https://www.ukm.my/jsm/english_journals/vol53num9_2024/contentsVol53num9_2024.html |
| spellingShingle | Kausar, Rehan Iqbal, Farhat Raziq, Abdul Sheikh, Naveed Rehman, Abdul Enhanced foreign exchange volatility forecasting using CEEMDAN with optuna-optimized ensemble deep learning model |
| title | Enhanced foreign exchange volatility forecasting using CEEMDAN with optuna-optimized ensemble deep learning model |
| title_full | Enhanced foreign exchange volatility forecasting using CEEMDAN with optuna-optimized ensemble deep learning model |
| title_fullStr | Enhanced foreign exchange volatility forecasting using CEEMDAN with optuna-optimized ensemble deep learning model |
| title_full_unstemmed | Enhanced foreign exchange volatility forecasting using CEEMDAN with optuna-optimized ensemble deep learning model |
| title_short | Enhanced foreign exchange volatility forecasting using CEEMDAN with optuna-optimized ensemble deep learning model |
| title_sort | enhanced foreign exchange volatility forecasting using ceemdan with optuna-optimized ensemble deep learning model |
| url | http://journalarticle.ukm.my/24507/ http://journalarticle.ukm.my/24507/ http://journalarticle.ukm.my/24507/1/SS%2025.pdf |