Forecasting Soyabean Crop Production using Arima Model
Year: 2025
Type: article
Abstract: In the realm of research, statistical modeling of non-stationary, non-linear statistics has grown to be a significant challenge. ANN and ARIMA are two of the most widely utilized models. This paper compares the Box-Jenkin’s and Artificial Neural Network (ANN) approaches for estimating the actual value of the soybean harvest in India. The primary goal of this investigation is to create a forecasting model that can accurately anticipate India's agricultural production. In order to predict the annual production of the soybean crop in India, a statistical forecasting model utilizing Box-Jenkin's approach and artificial neural networks was created throughout this research. The model's ability to forecast was assessed using Mean Absolute Percent Error (MAPE) and Root Mean Squared Error (RMSE). The annual predictions recommend that, over a ten-year period, soybean crop production should be measured with an accuracy of 90% and a regular deviation of 13%.
Authors: B. Saidulu, M. Raghavender Sharma
Language: English
Field: Decision Sciences
Domain: Social Sciences
SDG: Zero hunger
Open Access status: gold
OpenAlex ID: W4409521353