Author(s): Devra SJ, Patel DV, Shitap MS and Raj SR

Abstract: Time series modelling and forecasting is a vibrant research field that had attracted the interest of the scientific community in recent decades. Forecasts of agricultural prices are proposed to be useful for farmers, governments, policy makers and agribusiness industries. In this study, an effort is made to compare the forecasting capabilities of well-known linear Auto Regressive Integrated Moving Average (ARIMA) models, Time Delay Neural Network (TDNN) models and Hybrid (ARIMA-TDNN) models using data on monthly wholesale price of four major oilseed crops of India viz. groundnut, soybean, sesame and rapeseed and mustard from Jan-2001 to Dec-2021. Finally, the forecasting performance of these models are evaluated and compared by using common criteria’s such as; Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and percentage of forecasts of correct sign. Results showed that the lowest RMSE and MAE were achieved for the hybrid model than the ARIMA and ANN for all the four crops prices with the exception of MAPE which gave higher value and the percentage of forecasts of correct sign were achieved highest for the hybrid model than others. Key findings revealed that the Hybrid (ARIMA-ANN) model outperformed each individual ARIMA and ANN model, for forecasting of four major oilseed crops price.

DOI: 10.22271/maths.2023.v8.i4a.1098

Pages: 40-54 | Views: 229 | Downloads: 19

Download Full Article: Click Here