Modeling the Prediction of Stock Market Jumps Based on the Recurrent Neural Network and Deep Learning

Predicting crises and price jumps in the stock market and based on different models has been growing over the last decade. Due to the presence of big data, this issue has led to the growth of developments in the field of machine learning and deep learning models. Due to the importance of this issue, This study examined the ability of different machine learning models to predict the jumps in the total index of the Tehran Stock Exchange during the period 2013 to 2020. For this purpose, first stock market jumps were extracted based on the ARJI-GARCH approach and then these jumps were predicted by considering the possible effective variables including global and domestic markets. The prediction results of 1-, 3-, and 6-day periods for the out-of-sample period show that the machine learning method based on the long short-term memory (LSTM) network, a recurrent neural network, has a better result than other models.