Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrencies
The combination of Deep Learning and GARCH-type models has been proved to be superior to the single models in forecasting of volatility in various markets such as energy, main metals, and especially stock markets. To verify this hypothesis for cryptocurrencies market, we constructed various Deep Lea...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266682702300018X |
| _version_ | 1797796309189525504 |
|---|---|
| author | Bahareh Amirshahi Salim Lahmiri |
| author_facet | Bahareh Amirshahi Salim Lahmiri |
| author_sort | Bahareh Amirshahi |
| collection | DOAJ |
| description | The combination of Deep Learning and GARCH-type models has been proved to be superior to the single models in forecasting of volatility in various markets such as energy, main metals, and especially stock markets. To verify this hypothesis for cryptocurrencies market, we constructed various Deep Learning models based on Feed Forward Neural Networks (DFFNNs) and Long Short-Term Memory (LSTM) networks and evaluated their performance in forecasting the volatility of 27 cryptocurrencies. Then, different hybrid models were built in which the outputs of three GARCH-type models, namely GARCH, EGARCH, and APGARCH, with three different assumptions for the residuals’ distribution were fed into the DFFNN and LSTM networks. In other words, GARCH-type models were utilized as feature extractors and the deep learning models leveraged a sequence of extracted features as their inputs to produce the volatility of the next day. Our findings revealed that not only the deep learning models improve the forecasts of GARCH-type models with any distribution assumption, the forecasts of GARCH-type models as informative features can significantly increase the predictive power of the studied deep learning models; namely, the DFFNN and LSTM models. |
| first_indexed | 2024-03-13T03:31:07Z |
| format | Article |
| id | doaj.art-302323c211364492bcb8cb66529be3bb |
| institution | Directory Open Access Journal |
| issn | 2666-8270 |
| language | English |
| last_indexed | 2024-03-13T03:31:07Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj.art-302323c211364492bcb8cb66529be3bb2023-06-24T05:19:41ZengElsevierMachine Learning with Applications2666-82702023-06-0112100465Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrenciesBahareh Amirshahi0Salim Lahmiri1Department of Supply Chain and Business Technology Management, John Molson School of Business, Concordia University, Montreal, CanadaCorresponding author.; Department of Supply Chain and Business Technology Management, John Molson School of Business, Concordia University, Montreal, CanadaThe combination of Deep Learning and GARCH-type models has been proved to be superior to the single models in forecasting of volatility in various markets such as energy, main metals, and especially stock markets. To verify this hypothesis for cryptocurrencies market, we constructed various Deep Learning models based on Feed Forward Neural Networks (DFFNNs) and Long Short-Term Memory (LSTM) networks and evaluated their performance in forecasting the volatility of 27 cryptocurrencies. Then, different hybrid models were built in which the outputs of three GARCH-type models, namely GARCH, EGARCH, and APGARCH, with three different assumptions for the residuals’ distribution were fed into the DFFNN and LSTM networks. In other words, GARCH-type models were utilized as feature extractors and the deep learning models leveraged a sequence of extracted features as their inputs to produce the volatility of the next day. Our findings revealed that not only the deep learning models improve the forecasts of GARCH-type models with any distribution assumption, the forecasts of GARCH-type models as informative features can significantly increase the predictive power of the studied deep learning models; namely, the DFFNN and LSTM models.http://www.sciencedirect.com/science/article/pii/S266682702300018XDeep learningGARCH-family modelsCryptocurrencyVolatilityStatistical distribution |
| spellingShingle | Bahareh Amirshahi Salim Lahmiri Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrencies Machine Learning with Applications Deep learning GARCH-family models Cryptocurrency Volatility Statistical distribution |
| title | Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrencies |
| title_full | Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrencies |
| title_fullStr | Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrencies |
| title_full_unstemmed | Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrencies |
| title_short | Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrencies |
| title_sort | hybrid deep learning and garch family models for forecasting volatility of cryptocurrencies |
| topic | Deep learning GARCH-family models Cryptocurrency Volatility Statistical distribution |
| url | http://www.sciencedirect.com/science/article/pii/S266682702300018X |
| work_keys_str_mv | AT baharehamirshahi hybriddeeplearningandgarchfamilymodelsforforecastingvolatilityofcryptocurrencies AT salimlahmiri hybriddeeplearningandgarchfamilymodelsforforecastingvolatilityofcryptocurrencies |