The Model for Forecasting Livestock Production Using FB-Prophet

The article carries out an analysis, focusing on approaches to predicting the population of pigs in the Poltava region based on time series analysis methods. The research aims to enhance models that take into account the specific regional conditions, seasonal fluctuations, and the impact of external factors such as economic and social crises. The primary objective of the publication is to forecast the dynamics of pig population growth and to determine the optimal period for such forecasting. The Prophet model is utilized in this study, allowing for effective consideration of seasonal trends, thus ensuring high forecasting accuracy even in challenging economic conditions. The dynamics of the pig population during 2007–2024 are presented and illustrated graphically. An analysis of the statistical characteristics of the time series has been conducted, such as the mean value, standard deviation, minimum and maximum values, skewness, and kurtosis. The accuracy of the forecast has been determined and assessed using RMSE, MAE, and MAPE metrics for various forecasting horizons. The optimal forecasting period was found to be 12 months. The practical value of this study lies in the possibility of applying the obtained models for informed managerial decision-making in the field of agricultural livestock breeding. The use of such models contributes to the optimization of planning, production, storage, and sales processes, which allows for the reduction of risks associated with changes in market conditions and external threats. The developed approaches may serve as a foundation for the strategic planning of agrarian enterprises’ development, improving their economic indicators, and ensuring industry stability. The obtained results are valuable for both scientific research and practical activities in the agribusiness sector, providing support for managerial decisions at various levels – from operational planning to the development of regional development programs.