Stock Index Prediction using Artificial Neural Network and Econometric Model: The case of Nifty 50

  • Dr. Manu KS, Dr. Rameesha Kalra, Ms. Shubhika


Stocks are considered as the most volatile investment and are considered as risky. Forecasting and predicting of stock market returns is considered as an effective tool of risk minimization and portfolio diversification. Since the creation of organized stock exchanges in the world, efforts have been made by traders, investors, market intermediaries and academicians to forecast and predict the future price movements of stocks. Due to high volatility and market inefficiency, forecasting of prices becomes really difficult. A lot of analysis for the prediction of stock market prices like technical analysis, fundamental analysis and time series analysis is being carried out. But still the efficiency of the results from the analysis is still under question. So it becomes really necessary to find better and improved methods of predicting stock price. The study pertains to predict prices of Nifty 50 index. The daily closing prices of Nifty 50 Index are collected for a period of 5 year which starts from 1 April 2013 and ends on 31 March 2018. Further the data set is divided in the ratio 80:20, the 80% of the data is used to train the network and on the 20% of data the prediction is done. The study used Artificial Neural Network (ANN) using Backpropagation Algorithm and ARIMA (Auto Regressive Integrated Moving Average) in order to forecast the index prices. Overall, the study found pricing errors and it has been proved that ANN method outperforms ARIMA for forecasting of stock prices. Hence, ANN can be used by the investors who try to maximize their investments and earn better returns.

Keywords: Prediction, Stock Price, Nifty 50, ANN, ARIMA.

How to Cite
Dr. Manu KS, Dr. Rameesha Kalra, Ms. Shubhika. (2020). Stock Index Prediction using Artificial Neural Network and Econometric Model: The case of Nifty 50. International Journal of Advanced Science and Technology, 29(05), 3425 - 3437. Retrieved from