Please use this identifier to cite or link to this item:
Dautel, Alexander J.
Härdle, Wolfgang Karl
Lessmann, Stefan
Seow, Hsin-Vonn
Year of Publication: 
Series/Report no.: 
IRTG 1792 Discussion Paper No. 2019-008
Humboldt-Universität zu Berlin, International Research Training Group 1792 "High Dimensional Nonstationary Time Series", Berlin
Deep learning has substantially advanced the state-of-the-art in computer vision, natural language processing and other elds. The paper examines the potential of contemporary recurrent deep learning architectures for nancial time series forecasting. Considering the foreign exchange market as testbed, we systematically compare long short-term memory networks and gated recurrent units to traditional recurrent architectures as well as feedforward networks in terms of their directional forecasting accuracy and the profitability of trading model predictions. Empirical results indicate the suitability of deep networks for exchange rate forecasting in general but also evidence the diculty of implementing and tuning corresponding architectures. Especially with regard to trading pro t, a simpler neural network may perform as well as if not better than a more complex deep neural network.
Deep learning
Financial time series forecasting
Recurrent neural networks
Foreign exchange rates
Document Type: 
Working Paper

Files in This Item:

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.