Forecasting multi‐frequency intraday exchange rates using deep learning models

This paper examines the behavior of currencies' intraday exchange rates with mainly focuses on predicting these behaviors through deep learning models. The time series data are used in this study and comprise intraday exchange rate data for seven volatile currencies, recorded at two different frequency intervals: 1 h and 30 min. The data cover the time frame from January 1, 2018, to December 31, 2020. Firstly, wavelet maximal overlap discreet wavelet transform (MODWT) type “haar” is applied in order to identify the noise representing the volatile trend. Then learning models are applied to historical data that includes support vector regression (SVR), recurrent neural network (RNN), and long short‐term memory (LSTM). The main findings of the study provide strong evidence that the deep learning technique (i.e., LSTM) outperforms the other compatible models. This has been confirmed by the statistical measures for accuracy purposes. This study intends to address complex trends exhibited by volatile behavior of intraday exchange rates through non‐conventional learning techniques for the time of need‐based for the currency traders and other stakeholders.