Prospective Stock Analysis Model to improve the investment chances using Machine Learning

Abstract

The task of forecasting the stock market is not easy because it constitutes a chaotic mechanism which in initial conditions, can arbitrarily change the dynamics. Furthermore, in a competitive environment, as the stock market, the time series' non-linearity is pronounced which immediately impacts the performance of stock price forecasting. The stock price prediction models are divided into two scientific parameters, long-term or short-term. The short-term stock forecast relates to stock or future market forecasts for stock prices and trading strategies for a maximum period of several days between entry and departure. The idea behind these parameters is that the result of the prediction should have a higher accuracy rate than long-term predictions, considering that the stock market is highly competitive. To foresee the short-term, we are planning on incorporating Data Mining algorithms - LSTM (Long Short Term Memory) on the NSE stock market. We forecast prices from various industries based on the accuracy determined using the RMSE of all models. In order to make predictions more precise and appropriate, we have employed historical NSE stock market statistics and used a few Pre-processing processes.