Modelling and forecasting Nifty 50 using hybrid ARIMA-GARCH Model

Abstract

This study proposes an estimation technique for developing the best Öt ARIMA- GARCH model to predict the closing values of Nifty 50. The study put forward di§erent methods to resolve the issue of non-stationarity in mean as well as variance of the series before starting the estimation process. This study has applied autoregressive integrated moving- average (ARIMA), generalized autoregressive conditional heteroscedasticity (GARCH), ex- ponential GARCH (EGARCH) and threshold GARCH (TGARCH) model along with other estimation procedures on the daily closing prices of Nifty 50 from Jan 1, 2009 to Dec 30, 2019. Finally, the study identiÖes ARIMA(2,1,2)-EGARCH(1,1,1) as best model to predict the closing prices of Nifty 50. The Öndings indicate that the static forecast provides better results as compared to the dynamic forecast. These research Öndings will add to the tool kit of domestic as well as international portfolio managers and investors to frame suitable NIFTY trade strategies with least possible risks.