A0194
Title: Can higher data frequency lead to more accurate stock market predictions: Nasdaq 100 and DAX cases
Authors: Nuno Ferreira - ISCTE-IUL (Portugal) [presenting]
Diana Aldea Mendes - ISCTE-IUL Lisbon (Portugal)
Vivaldo Mendes - ISCTE-IUL (Portugal)
Abstract: The aim is to assess if the frequency of time series is associated with increased forecast accuracy. Two different time series from the G7 countries, the NASDAQ100 and the DAX, are examined for a period of five minutes, as well as daily frequency. The employed algorithms are deep learning recurrent neural networks that are particularly suited for a variety of variations of Long Short-Term Memory (LSTM) structures (LSTM, BiLSTM). A random search over the hyperparameters was employed to determine the architecture that minimizes the loss function. A better outcome is obtained for the 5-minute daily frequency for both datasets, with the forecast increased by 1\%.
