Realised volatility prediction of high-frequency data with jumps based on machine learning
Asset price jumps are very common in financial markets, and they are essential to accurately predict volatility. This article focuses on 50 randomly selected stocks from the Chinese stock market, utilising high-frequency data to construct two jump models, the heterogeneous autoregressive quarticity...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/09540091.2023.2210265 |
| _version_ | 1797683982876278784 |
|---|---|
| author | Gao Yuyan He di Mu Yan Zhao Hongmin |
| author_facet | Gao Yuyan He di Mu Yan Zhao Hongmin |
| author_sort | Gao Yuyan |
| collection | DOAJ |
| description | Asset price jumps are very common in financial markets, and they are essential to accurately predict volatility. This article focuses on 50 randomly selected stocks from the Chinese stock market, utilising high-frequency data to construct two jump models, the heterogeneous autoregressive quarticity jump model (HARQ-J) and the full heterogeneous autoregressive quarticity jump model (HARQ-F-J), which take into account jump variables based on existing models (HARQ and HARQ-F). To further enhance the accuracy of our volatility forecasts, the study combines the newly constructed models with the machine learning (ML) to form a hybrid model. Finally, the empirical research shows that the new hybrid model performs better than existing traditional prediction methods. In particular, the long- and short-term memory (LSTM) function is significantly better than other machine learning functions. Among all the LSTM models tested by the model confidence set (MCS), the HARQ-F-J-LSTM model has the highest prediction accuracy, followed by the HARQ-J-LSTM model. |
| first_indexed | 2024-03-12T00:22:47Z |
| format | Article |
| id | doaj.art-122628cd50de401a80fd40811b162769 |
| institution | Directory Open Access Journal |
| issn | 0954-0091 1360-0494 |
| language | English |
| last_indexed | 2024-03-12T00:22:47Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj.art-122628cd50de401a80fd40811b1627692023-09-15T10:48:02ZengTaylor & Francis GroupConnection Science0954-00911360-04942023-12-0135110.1080/09540091.2023.22102652210265Realised volatility prediction of high-frequency data with jumps based on machine learningGao Yuyan0He di1Mu Yan2Zhao Hongmin3Nanjing University of Finance and EconomicsNanjing UniversityNanjing University of Finance and EconomicsNanjing University of Finance and EconomicsAsset price jumps are very common in financial markets, and they are essential to accurately predict volatility. This article focuses on 50 randomly selected stocks from the Chinese stock market, utilising high-frequency data to construct two jump models, the heterogeneous autoregressive quarticity jump model (HARQ-J) and the full heterogeneous autoregressive quarticity jump model (HARQ-F-J), which take into account jump variables based on existing models (HARQ and HARQ-F). To further enhance the accuracy of our volatility forecasts, the study combines the newly constructed models with the machine learning (ML) to form a hybrid model. Finally, the empirical research shows that the new hybrid model performs better than existing traditional prediction methods. In particular, the long- and short-term memory (LSTM) function is significantly better than other machine learning functions. Among all the LSTM models tested by the model confidence set (MCS), the HARQ-F-J-LSTM model has the highest prediction accuracy, followed by the HARQ-J-LSTM model.http://dx.doi.org/10.1080/09540091.2023.2210265realised volatilityjumpneural networkmcs test |
| spellingShingle | Gao Yuyan He di Mu Yan Zhao Hongmin Realised volatility prediction of high-frequency data with jumps based on machine learning Connection Science realised volatility jump neural network mcs test |
| title | Realised volatility prediction of high-frequency data with jumps based on machine learning |
| title_full | Realised volatility prediction of high-frequency data with jumps based on machine learning |
| title_fullStr | Realised volatility prediction of high-frequency data with jumps based on machine learning |
| title_full_unstemmed | Realised volatility prediction of high-frequency data with jumps based on machine learning |
| title_short | Realised volatility prediction of high-frequency data with jumps based on machine learning |
| title_sort | realised volatility prediction of high frequency data with jumps based on machine learning |
| topic | realised volatility jump neural network mcs test |
| url | http://dx.doi.org/10.1080/09540091.2023.2210265 |
| work_keys_str_mv | AT gaoyuyan realisedvolatilitypredictionofhighfrequencydatawithjumpsbasedonmachinelearning AT hedi realisedvolatilitypredictionofhighfrequencydatawithjumpsbasedonmachinelearning AT muyan realisedvolatilitypredictionofhighfrequencydatawithjumpsbasedonmachinelearning AT zhaohongmin realisedvolatilitypredictionofhighfrequencydatawithjumpsbasedonmachinelearning |