A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search Algorithm
The return series of cryptocurrencies, which are emerging digital assets, exhibit nonstationarity, nonlinearity, and volatility clustering compared to other traditional financial markets, making them exceptionally difficult to forecast. Therefore, accurate cryptocurrency price forecasting is essenti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9785838/ |
| _version_ | 1828218152332296192 |
|---|---|
| author | Xiaoxu Du Zhenpeng Tang Junchuan Wu Kaijie Chen Yi Cai |
| author_facet | Xiaoxu Du Zhenpeng Tang Junchuan Wu Kaijie Chen Yi Cai |
| author_sort | Xiaoxu Du |
| collection | DOAJ |
| description | The return series of cryptocurrencies, which are emerging digital assets, exhibit nonstationarity, nonlinearity, and volatility clustering compared to other traditional financial markets, making them exceptionally difficult to forecast. Therefore, accurate cryptocurrency price forecasting is essential for market participants and regulators. It has been demonstrated that improved data forecasting accuracy can be achieved through decomposition, but few researchers have performed information extraction on the residual series generated by data decomposition. Based on the construction of a “decomposition-optimization-integration” hybrid model framework, in this paper, we propose a multi-scale hybrid forecasting model that combines the residual components after primary decomposition for secondary decomposition and integration. This model uses the variational modal decomposition (VMD) method to decompose the original return series into a finite number of components and residual terms. Then, the residual terms are decomposed, and the features are extracted using the completed ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method. The components are predicted by an extreme learning machine optimized by the sparrow search algorithm, and the final predictions are summed to obtain the final results. Forecasts for the returns of Bitcoin and Ethereum, which are significant cryptocurrency assets, are compared with other benchmark models constructed based on different ideas. We find that the proposed quadratic decomposition VMD-Res.-CEEMDAN-SSA-ELM hybrid model demonstrates the optimal and most stable forecasting performance in both one-step and multi-step ahead prediction of the cryptocurrency return series. |
| first_indexed | 2024-04-12T15:58:32Z |
| format | Article |
| id | doaj.art-ab08c174f6b0449a954b5345f4c180d6 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T15:58:32Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ab08c174f6b0449a954b5345f4c180d62022-12-22T03:26:17ZengIEEEIEEE Access2169-35362022-01-0110603976041110.1109/ACCESS.2022.31793649785838A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search AlgorithmXiaoxu Du0https://orcid.org/0000-0001-9915-5923Zhenpeng Tang1https://orcid.org/0000-0002-8376-2128Junchuan Wu2Kaijie Chen3Yi Cai4School of Economics and Management, Fuzhou University, Fuzhou, ChinaSchool of Economics and Management, Fujian Agriculture and Forestry University, Fuzhou, ChinaSchool of Economics and Management, Nanchang University, Nanchang, ChinaSchool of Economics and Management, Fuzhou University, Fuzhou, ChinaSchool of Economics and Management, Fuzhou University, Fuzhou, ChinaThe return series of cryptocurrencies, which are emerging digital assets, exhibit nonstationarity, nonlinearity, and volatility clustering compared to other traditional financial markets, making them exceptionally difficult to forecast. Therefore, accurate cryptocurrency price forecasting is essential for market participants and regulators. It has been demonstrated that improved data forecasting accuracy can be achieved through decomposition, but few researchers have performed information extraction on the residual series generated by data decomposition. Based on the construction of a “decomposition-optimization-integration” hybrid model framework, in this paper, we propose a multi-scale hybrid forecasting model that combines the residual components after primary decomposition for secondary decomposition and integration. This model uses the variational modal decomposition (VMD) method to decompose the original return series into a finite number of components and residual terms. Then, the residual terms are decomposed, and the features are extracted using the completed ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method. The components are predicted by an extreme learning machine optimized by the sparrow search algorithm, and the final predictions are summed to obtain the final results. Forecasts for the returns of Bitcoin and Ethereum, which are significant cryptocurrency assets, are compared with other benchmark models constructed based on different ideas. We find that the proposed quadratic decomposition VMD-Res.-CEEMDAN-SSA-ELM hybrid model demonstrates the optimal and most stable forecasting performance in both one-step and multi-step ahead prediction of the cryptocurrency return series.https://ieeexplore.ieee.org/document/9785838/Cryptocurrencymodel selectiondecomposition-ensembleextreme learning machinesparrow search algorithm |
| spellingShingle | Xiaoxu Du Zhenpeng Tang Junchuan Wu Kaijie Chen Yi Cai A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search Algorithm IEEE Access Cryptocurrency model selection decomposition-ensemble extreme learning machine sparrow search algorithm |
| title | A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search Algorithm |
| title_full | A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search Algorithm |
| title_fullStr | A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search Algorithm |
| title_full_unstemmed | A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search Algorithm |
| title_short | A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search Algorithm |
| title_sort | new hybrid cryptocurrency returns forecasting method based on multiscale decomposition and an optimized extreme learning machine using the sparrow search algorithm |
| topic | Cryptocurrency model selection decomposition-ensemble extreme learning machine sparrow search algorithm |
| url | https://ieeexplore.ieee.org/document/9785838/ |
| work_keys_str_mv | AT xiaoxudu anewhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm AT zhenpengtang anewhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm AT junchuanwu anewhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm AT kaijiechen anewhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm AT yicai anewhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm AT xiaoxudu newhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm AT zhenpengtang newhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm AT junchuanwu newhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm AT kaijiechen newhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm AT yicai newhybridcryptocurrencyreturnsforecastingmethodbasedonmultiscaledecompositionandanoptimizedextremelearningmachineusingthesparrowsearchalgorithm |