Forecasting Duck Production in Egypt by using the ARIMA Model

Time series forecasting plays a vital role in veterinary medicine, enabling predictive insights into disease outbreaks, production trends, and health outcomes. Among the multitude of methods available for time series forecasting, the Autoregressive Integrated Moving Average (ARIMA) model stands out for its simplicity and effectiveness. In this study, we focused on autocorrelation and illustrated the recommended steps ARIMA methods via analysis of the time series of duck numbers produced annually in Egypt during the period from 2003 to 2022, provided by the Central Agency for Public Mobilization and Statistics. The Mean Absolute Error (MAE), R-squared ( ), Root Mean Square Error (RMSE), and Mean Absolute Percent Error (MAPE) were used as selection criteria to compare models and select the best one. Depending on these measures, the ARIMA model with ordering (1,1,0) is considered the best model for the forecasting process. The model fit statistics, such as RMSE (2024.232), which was low, and the lowest Bayesian Information Criterion (BIC) value (15.536) indicate that the model fit the data well. The value (0.463) indicates a reasonably good forecasting performance.. Annual duck production forecasts provide valuable insights for veterinary practice. They support risk-based surveillance, optimize vaccine and diagnostic resource allocation, and enhance biosecurity during high-production periods. Such predictions improve disease preparedness and strengthen food safety within a One Health framework. The ARIMA model (1,1,0) demonstrated reasonable performance in forecasting annual duck production (.463). However, the prediction intervals were relatively wide, which can be attributed to the limited length of the available time series. Therefore, future studies are recommended to employ longer datasets and to explore more advanced forecasting approaches, such as machine learning methods, to improve predictive accuracy and reliability.