dc.contributor.author | Mouton, J. | |
dc.contributor.author | Hoffman, A.J. | |
dc.date.accessioned | 2017-02-02T09:25:37Z | |
dc.date.available | 2017-02-02T09:25:37Z | |
dc.date.issued | 2014 | |
dc.identifier.citation | Mouton, J. & Hoffman, A.J. 2014. Combining empirical mode decomposition with neural networks for the prediction of exchange rates. Proceedings of the International Conference on Neural Computation Theory and Applications (NCTA-2014):244-249. [http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220%2f0005130702440249] | en_US |
dc.identifier.isbn | 978-989-758-054-3 | |
dc.identifier.uri | http://hdl.handle.net/10394/19945 | |
dc.identifier.uri | http://dx.doi.org/10.5220/0005130702440249 | |
dc.identifier.uri | http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0005130702440249 | |
dc.description.abstract | This paper proposes a neural network based model applied to empirical mode decomposition (EMD) filtered data for multi-step-ahead prediction of exchange rates. EMD is used to decompose the returns of exchange rates into intrinsic mode functions (IMFs) which are partially recomposed to produce a low-pass filtered time series. This series is used to train a neural network for multi-step-ahead prediction. Out-of-sample tests on EUR/USD and USD/JPY rates show superior performance compared to random walk and neural network models that do not employ EMD filtering. The novel approach of using EMD as a filtering technique in combination with neural networks consistently delivers higher returns on investment and demonstrates its utility in multi-step-ahead prediction | en_US |
dc.language.iso | en | en_US |
dc.publisher | SCITEPRESS (Science and Technology Publications, Lda.) | en_US |
dc.subject | Empirical Mode Decomposition (EMD) | en_US |
dc.subject | Artificial neural network | en_US |
dc.subject | Foreign exchange rate forecasting | en_US |
dc.title | Combining empirical mode decomposition with neural networks for the prediction of exchange rates | en_US |
dc.type | Presentation | en_US |
dc.contributor.researchID | 10196978 - Hoffman, Alwyn Jakobus | |