Modelling Stock Market and Future Derivative Market Volatility in India

Abstract

In financial market, various shares, bonds, securities or newlinecurrencies are traded on the daily basis, thus making most of the newlinedatasets as time series data where price is plotted against a time newlineseries. There are many techniques that can be used with time series newlinedata like ARIMA Model, Exponential smoothing, Neural Networks or newlineSimple moving average. However ARIMA Model is commonly used to newlineunderstand time series analysis in order to extract meaningful newlinecharacteristics of the data and help in prediction of the stock and newlinederivative prices. Since it helps to understand what happened in past newlineand past behavior of data can help to predict future. Time series is a newlinespecial property and different set of predictive algorithm. In this newlineresearch key components of time series data have been discussed and newlineimplemented using ARIMA model. The data comprises of time series newlinedata on 18 companies and one index from NSE of India. The daily newlineclosing price of the stocks and index are considered for the spot newlinemarket, the near month contract has been used to analyse the stock newlineand index future market.Using ARIMA model the investor can predict newlinethe spot and future market prices. To a certain extent, it represents newlinethe overall trend of spot and futures market prices and the forecasting newlineresults have some reference value for investors. Therefore investors newlinecan refer to the model established in this study to build their own newlineportfolios newline