Previsão de preço de frango e de suíno vivo: uma comparação entre os modelos Prophet e NeuralProphet
Abstract
ABSTRACT
Forecasting the price movements of broilers and swine, due to all the uncertainties involved, is a very complex challenge. In this context, this work aims to compare the performance of models, based on the Prophet and NeuralProphet tools, in forecasting, in the state of Paraná, average prices of broilers and swine. The database presents, for the period between January/2007 and June/2024, five historical series: average price of live broiler, average price of live swine, accumulated monthly precipitation, average monthly temperature, and duration of the Covid pandemic. Forecasting models, based on the Prophet and NeuralProphet tools, were implemented in the Python language. The results obtained from the two forecasting models were compared using the Mean Absolute Percentage Error (MAPE), the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). It was found that, for a 12-month horizon, the multivariate NeuralProphet model obtained the best forecasting performance in predicting the average prices of broilers and live swine.
Copyright (c) 2026 REVISTA CEREUS

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
DECLARAÇÃO DE TRANSFERÊNCIA DE DIREITOS AUTORAIS
Os autores do manuscrito submetido declaram ter conhecimento que em caso de aceitação do artigo, a Revista Cereus, passa a ter todos os direitos autorais sobre o mesmo. O Artigo será de propriedade exclusiva da Revista, sendo vedada qualquer reprodução, em qualquer outra parte ou meio de divulgação, impressa ou eletrônica.