2026-04-14T05:45:49Zhttps://recercat.cat/oai/request

oai:recercat.cat:2445/1826012025-12-05T10:16:50Zcom_2072_1057col_2072_478771col_2072_478911col_2072_478917

00925njm 22002777a 4500 dc Clavería González, Óscar author Monte Moreno, Enric author Sorić, Petar author Torra Porras, Salvador author 2022-01-24T22:03:02Z 2022-01-24T22:03:02Z 2022 This 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. Valor (Economia) Xarxes neuronals convolucionals Previsió econòmica Convolutional neural networks Value Economic forecasting An application of deep learning for exchange rate forecasting