Comparison of ARIMA, SutteARIMA, and Holt-Winters, and NNAR Models to Predict Food Grain in India

Forecasting

article

Ansari Saleh Ahmar¹  Pawan Kumar Singh²  R. Ruliana¹  Alok Kumar Pandey⁴  Stuti Gupta⁵ 

[1] Department of Statistics, Universitas Negeri Makassar;School of Humanities and Social Sciences, Thapar Institute of Engineering and Technology;Department of Economics, Lakshmibai College, University of Delhi;Centre for the Integrated and Rural Development, Banaras Hindu University;RamManohar Lohia University

关键词: ARIMA;    SutteARIMA;    NNAR;    Holt-Winters;    food grain;   

DOI  :  10.3390/forecast5010006

学科分类：陶瓷学

来源: mdpi

【 摘 要 】

The agriculture sector plays an essential function within the Indian economic system. Foodgrains provide almost all the calories and proteins. This paper aims to compare ARIMA, SutteARIMA, Holt-Winters, and NNAR models to recommend an effective model to predict foodgrains production in India. The execution of the SutteARIMA predictive model used in this analysis was compared with the established ARIMA, Neural Network Auto-Regressive (NNAR), and Holt-Winters models, which have been widely applied for time series prediction. The findings of this study reveal that both the SutteARIMA model and the Holt-Winters model performed well with real-life problems and can effectively and profitably be engaged for food grain forecasting in India. The food grain forecasting approach with the SutteARIMA model indicated superior performance over the ARIMA, Holt-Winters, and NNAR models. Indeed, the actual and predicted values of the SutteARIMA and Holt-Winters forecasting models are quite close to predicting foodgrains production in India. This has been verified by MAPE and MSE values that are relatively low with the SutteARIMA model. Therefore, India’s SutteARIMA model was used to predict foodgrains production from 2021 to 2025. The forecasted amount of respective crops are as follows (in lakh tonnes) 1140.14 (wheat), 1232.27 (rice), 466.46 (coarse), 259.95 (pulses), and a total 3069.80 (foodgrains) by 2025.

【 授权许可】

CC BY