Cross Entropy Based Long Short Term Memory Recurrent Neural Network Model for Analyzing the Time Series on Stock Market Price

Abstract

In the financial stock market, a sequence of prices obtained from the share market with respect to the time series is usually examined. Generally, time series in finance, particularly shows importance in predicting investment in today's share market. Since there are too many factors such as public opinions, general economic conditions, or political events, vulnerability in the economy are directly or indirectly reflects on the evolution of financial time series. The desire of the investor is to predict the future stock prices neglecting whether the investor is a long-term investor or a day-trader. A major challenge is to develop and design an efficient predictive model that guides investors to make appropriate decisions. In this research work, Long Short Term Memory-Recurrent Neural Network (LSTM-RNN) is developed to overcome such disputes and contributing an efficient technique for predicting the future stock prices financially. In addition to the model, cross entropy is calculated using a Mutual Information feature selection model to minimize the optimization problems that create the time complexity in the system. The proposed LSTM-RNN has achieved best accuracy of 61.33% of prediction accuracy compared to state-of-the-art techniques.