Predictive Analysis and Forecasting of S&P CNX NIFTY50 using Stochastic Models

Abstract

Stock price prediction plays an important role in finance and economics which has encouraged the interest of researchers over the years to develop better predictive models. While looking at the share market structure which involves lots of risk, time series forecasting is an effective area of research. It provides with simple and faster computations for enormous amount of data. This manuscript focuses on forecasting future values for S & P CNX NIFTY 50 using its history indices (January 2008-December 2016). The statistical methods are used to forecast future values in advance. The findings after applying several models on the data and comparing the error values, the mean error of Exponential Smoothing Model (EST) is found to be having the least error values and have a better prediction rate.