Please use this identifier to cite or link to this item: http://hdl.handle.net/2445/182601
Full metadata record
DC FieldValueLanguage
dc.contributor.authorClavería González, Óscar-
dc.contributor.authorMonte Moreno, Enric-
dc.contributor.authorSorić, Petar-
dc.contributor.authorTorra Porras, Salvador-
dc.date.accessioned2022-01-24T22:03:02Z-
dc.date.available2022-01-24T22:03:02Z-
dc.date.issued2022-
dc.identifier.urihttp://hdl.handle.net/2445/182601-
dc.description.abstractThis paper examines the performance of several state-of-the-art deep learning techniques for exchange rate forecasting (deep feedforward network, convolutional network and a long short-term memory). On the one hand, the configuration of the different architectures is clearly detailed, as well as the tuning of the parameters and the regularisation techniques used to avoid overfitting. On the other hand, we design an out-of-sample forecasting experiment and evaluate the accuracy of three different deep neural networks to predict the US/UK foreign exchange rate in the days after the Brexit took effect. Of the three configurations, we obtain the best results with the deep feedforward architecture. When comparing the deep learning networks to time-series models used as a benchmark, the obtained results are highly dependent on the specific topology used in each case. Thus, although the three architectures generate more accurate predictions than the time-series models, the results vary considerably depending on the specific topology. These results hint at the potential of deep learning techniques, but they also highlight the importance of properly configuring, implementing and selecting the different topologies.ca
dc.format.extent44 p.-
dc.format.mimetypeapplication/pdf-
dc.language.isoengca
dc.publisherUniversitat de Barcelona. Facultat d'Economia i Empresaca
dc.relation.isformatofReproducció del document publicat a: http://www.ub.edu/irea/working_papers/2022/202201.pdf-
dc.relation.ispartofIREA – Working Papers, 2022, IR22/01-
dc.relation.ispartofAQR – Working Papers, 2022, AQR22/01-
dc.relation.ispartofseries[WP E-IR22/01]ca
dc.relation.ispartofseries[WP E-AQR22/01]-
dc.rightscc-by-nc-nd, (c) Clavería González et al., 2022-
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subject.classificationValor (Economia)-
dc.subject.classificationXarxes neuronals convolucionals-
dc.subject.classificationPrevisió econòmica-
dc.subject.otherConvolutional neural networks-
dc.subject.otherValue-
dc.subject.otherEconomic forecasting-
dc.titleAn application of deep learning for exchange rate forecastingca
dc.typeinfo:eu-repo/semantics/workingPaperca
dc.rights.accessRightsinfo:eu-repo/semantics/openAccessca
Appears in Collections:AQR (Grup d’Anàlisi Quantitativa Regional) – Working Papers
Documents de treball (Institut de Recerca en Economia Aplicada Regional i Pública (IREA))

Files in This Item:
File Description SizeFormat 
IR22_001_Claveria et al.pdf1.86 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons