2024, Vol. 9, Issue 2, Part B

In this paper, Seasonal Autoregressive Integrated Moving Average (SARIMA), Generalized Autoregressive Conditional Heteroskedasticity (GARCH) and Hybrid (SARIMA-GARCH) models have been used for modelling the prices of tomato in Panipat APMC (Agricultural Produce Market Committee) market of Haryana. Akaike information criteria (AIC) and Bayesian information criteria (BIC) have been used as model selection criteria. And, forecasting performance measure such as relative percentage deviation (RD (%)), mean absolute deviation error (MAPE) and standard error of prediction (SEP) have also been used to check the accuracy of the fitted models. The results of present study showed that the performance of Hybrid models was more appropriate as compared to SARIMA and GARCH models for predicting the price of agricultural product (tomato). The findings of the present study will help in taking decisions in managing agricultural supplies.