Forecasting Volatility in Indian Stock Market using Artificial Neural Network with Multiple Inputs and Outputs

TL;DR

This paper develops neural network models with multiple inputs to forecast volatility in the Indian stock market, incorporating various global market indicators, and evaluates their effectiveness over different periods.

Contribution

It introduces a neural network approach using multiple global market volatility indicators to predict Indian stock market volatility, which is a novel application in this context.

Findings

Neural network models effectively predict Indian market volatility.

Inclusion of global volatility indicators improves prediction accuracy.

Model performance varies across different time periods.

Abstract

Volatility in stock markets has been extensively studied in the applied finance literature. In this paper, Artificial Neural Network models based on various back propagation algorithms have been constructed to predict volatility in the Indian stock market through volatility of NIFTY returns and volatility of gold returns. This model considers India VIX, CBOE VIX, volatility of crude oil returns (CRUDESDR), volatility of DJIA returns (DJIASDR), volatility of DAX returns (DAXSDR), volatility of Hang Seng returns (HANGSDR) and volatility of Nikkei returns (NIKKEISDR) as predictor variables. Three sets of experiments have been performed over three time periods to judge the effectiveness of the approach.