Artificial Neural Network Based Non-linear Transformation of High-Frequency Returns for Volatility Forecasting
This paper uses Long Short Term Memory Recurrent Neural Networks to extract information from the intraday high-frequency returns to forecast daily volatility. Applied to the IBM stock, we find significant improvements in the forecasting performance of models that use this extracted information compa...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-02-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2021.787534/full |
| _version_ | 1818897286050086912 |
|---|---|
| author | Christian Mücher Christian Mücher |
| author_facet | Christian Mücher Christian Mücher |
| author_sort | Christian Mücher |
| collection | DOAJ |
| description | This paper uses Long Short Term Memory Recurrent Neural Networks to extract information from the intraday high-frequency returns to forecast daily volatility. Applied to the IBM stock, we find significant improvements in the forecasting performance of models that use this extracted information compared to the forecasts of models that omit the extracted information and some of the most popular alternative models. Furthermore, we find that extracting the information through Long Short Term Memory Recurrent Neural Networks is superior to two Mixed Data Sampling alternatives. |
| first_indexed | 2024-12-19T19:13:45Z |
| format | Article |
| id | doaj.art-78d349c76c94474f9a3726b1e1aa8820 |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-12-19T19:13:45Z |
| publishDate | 2022-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-78d349c76c94474f9a3726b1e1aa88202022-12-21T20:09:12ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122022-02-01410.3389/frai.2021.787534787534Artificial Neural Network Based Non-linear Transformation of High-Frequency Returns for Volatility ForecastingChristian Mücher0Christian Mücher1Chair of Statistics and Econometrics, University of Freiburg, Freiburg, GermanyGraduate School of Decision Sciences, University of Konstanz, Konstanz, GermanyThis paper uses Long Short Term Memory Recurrent Neural Networks to extract information from the intraday high-frequency returns to forecast daily volatility. Applied to the IBM stock, we find significant improvements in the forecasting performance of models that use this extracted information compared to the forecasts of models that omit the extracted information and some of the most popular alternative models. Furthermore, we find that extracting the information through Long Short Term Memory Recurrent Neural Networks is superior to two Mixed Data Sampling alternatives.https://www.frontiersin.org/articles/10.3389/frai.2021.787534/fullneural networksforecastinghigh-frequency datarealized volatilitymixed data samplinglong short term memory |
| spellingShingle | Christian Mücher Christian Mücher Artificial Neural Network Based Non-linear Transformation of High-Frequency Returns for Volatility Forecasting Frontiers in Artificial Intelligence neural networks forecasting high-frequency data realized volatility mixed data sampling long short term memory |
| title | Artificial Neural Network Based Non-linear Transformation of High-Frequency Returns for Volatility Forecasting |
| title_full | Artificial Neural Network Based Non-linear Transformation of High-Frequency Returns for Volatility Forecasting |
| title_fullStr | Artificial Neural Network Based Non-linear Transformation of High-Frequency Returns for Volatility Forecasting |
| title_full_unstemmed | Artificial Neural Network Based Non-linear Transformation of High-Frequency Returns for Volatility Forecasting |
| title_short | Artificial Neural Network Based Non-linear Transformation of High-Frequency Returns for Volatility Forecasting |
| title_sort | artificial neural network based non linear transformation of high frequency returns for volatility forecasting |
| topic | neural networks forecasting high-frequency data realized volatility mixed data sampling long short term memory |
| url | https://www.frontiersin.org/articles/10.3389/frai.2021.787534/full |
| work_keys_str_mv | AT christianmucher artificialneuralnetworkbasednonlineartransformationofhighfrequencyreturnsforvolatilityforecasting AT christianmucher artificialneuralnetworkbasednonlineartransformationofhighfrequencyreturnsforvolatilityforecasting |