Comparison of time series forecasting models: an analysis between Prophet and SARIMA.
Keywords:
Time series, Forecasting, Prophet, SARIMAAbstract
This study presents a time series analysis with the main objective of comparing the performance of two widely used forecasting models: Prophet and SARIMA. The methodology adopted included an exploratory stage, stationarity verification using the ADF test, autocorrelation analysis (ACF/PACF), and decomposition of the series into trend, seasonality, and residuals. To evaluate performance, the error metrics MAE and RMSE were used, in addition to cross-validation in the case of Prophet. The results show that the SARIMA model outperformed Prophet. However, it is concluded that the combined use of different approaches can provide a more robust and consistent analysis.
References
SERVIN, Victor. Understanding time-series data and why it matters. AWS Database Blog, 12 nov. 2024. Disponível em: https://aws.amazon.com/pt/blogs/database/understanding-time-series-data-and-why-it-matters/
GRUPO POTENCIAL. Quais fatores influenciam o preço do petróleo? Gazeta do Povo (conteúdo publicitário), 9 ago. 2022. Disponível em: https://www.gazetadopovo.com.br/conteudo-publicitario/grupo-potencial/quais-fatores-influenciam-o-preco-do-petroleo/
PORTO, Bruno Matos; PHILIPPI, Daniela Althoff. Previsão de séries temporais de petróleo por meio de redes neurais. Encontro da Associação Nacional de Pós-Graduação e Pesquisa em Administração (EnANPAD). Anais… Curitiba: XLII EnANPAD, 2018b. Disponível em: https://tinyurl.com/y9l6y59d.
INSTITUTO DE PESQUISA ECONÔMICA APLICADA (IPEA). Commodities – petróleo – cotação internacional (IFS12_PETROLEUM12). 2025. Disponível em: http://www.ipeadata.gov.br
Fonte original: Fundo Monetário Internacional (FMI), International Financial Statistics (IFS). Série mensal de jan. 1957 a jul. 2025. Unidade: US$ por barril. Última atualização em: 19 ago. 2025.
TAYLOR, Sean J.; LETHAM, Benjamin. Prophet: forecasting at scale. 2017. Disponível em: https://facebook.github.io/prophet/
ALURA. Métricas de avaliação para séries temporais. 8 jun. 2021. Disponível em: https://www.alura.com.br/artigos/metricas-de-avaliacao-para-series-temporais
ARAUJO, Ricardo CA; FERREIRA, Paulo H. Modelos de previsao de preços no mercado de combustıveis.
FENG, Tianyu; ZHOU, Zheng; XU, Jiaying; LIU, Minghui; LI, Ming; JIA, Huanhuan; YU, Xihe. The comparative analysis of SARIMA, Facebook Prophet, and LSTM for road traffic injury prediction in Northeast China. Frontiers in Public Health, v. 10, 946563, 2022. DOI: 10.3389/fpubh.2022.946563.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Silvio Fernando Alves Xavier, Patricia Virginia de Santana , Denilson de Oliveira Silva
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish in the Annals of Data Analysis retain
the copyright of their work and agree to license it under a Creative Commons Attribution-
NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license.
