Stock price prediction using deep learning methods in high-frequency trading

The stock market analysis examines and evaluates the stock market by considering the financial, political, and social indicators to make future predictions. Breakthrough results of advancements in big data and deep learning technologies attract the attention of researchers and traders to computer-assisted stock market analysis. There are several studies on stock market analysis using conventional machine learning and deep learning models. In this paper, we used Autoregressive Integrated Moving Average (ARIMA) as a base model and compared it with three different models of Recurrent Neural Networks: Long Short-Term Memory (LSTM) networks, Gated Recurrent Unit (GRU), LSTM with an attention layer model. We compare the results and performance of four different models on Borsa Istanbul data while making intraday predictions. Even though the LSTM results are very close to the GRU model, GRU slightly outperforms the others.