PREDICTING STOCK MARKET INDICES USING NEURAL NETWORKS

Investing in stock markets is a decisive role for every investor. Speculation in the market makes an investor distressed about his investment. Hence predicting the exact stock market price at high accuracy helps investors to invest wisely to yield more returns. Most of the literature has been carried in predicting the stock market prices using various Logistic regression, ARIMA and machine learning techniques. This paper aims at predicting the stock indices of developed markets and emerging markets using deep learning neural network techniques i.e., Artificial Neural Networks (ANN) and Recurrent Neural Network (RNN). The data consists of daily prices open, close, high, and low, volume of NIFTY 50, S&P 500, New York Stock Index, Korean Stock Index and Dow Jones Index Jan 2014 to July 2019. The open price of the index is fed as input to the models. This study predicts the next day index and gives a comparative analysis between the two models based on the accuracy of prediction. Based on the performance of the models, the best model would be suggested to the investors for the investor