Arabica coffee price forecast: a neural network application CNN-BLSTM
DOI:
https://doi.org/10.33448/rsd-v11i3.26101Keywords:
Artificial neural networks; Arabica coffee; Keras; Python.Abstract
This work proposes the use of the CNN-BLSTM neural network as a tool to predict the price of arabica coffee. The database provided by CEPEA (Center for Advanced Studies in Applied Economics) presents a historical series of the price of arabica coffee, in the period between January 1997 and December 2021. Forecast models based on neural networks LSTM, BLSTM, CNN and CNN-BLSTM were implemented, in the Python language, using the Keras framework. Results obtained, from the four models, were compared using MAE, RMSE and MAPE metrics. It was verified, for a horizon of 6 months, that the CNN-BLSTM model presented better performance.
References
Aurigliett, L. M. M. & Tonin, J. M. (2021). Relação entre base, volatilidade e liquidez: evidências para o mercado futuro de café no Brasil. Revista AE&S, 2(1), 1-4. https://doi.org/10.22167/2675-20210003.
Althelaya, K. A. (2018). Evaluation of bidirectional LSTM for short and long term stock market prediction. In: International Conference on Information as Communication System (ICICS), Irbid, Jordan.
Ayyanathan, N. & Kannammal, A. (2014). Share price time series forecasting for effective supply chain information Exchange. International Journal of Logistics Systems and Management, 18(1). https://doi.org/10.1504/IJLSM.2014.062125.
Barros, D. (2021). Dados sobre Café no Brasil: Consumo, Produção e Exportação. Disponível em: https://reviewcafe.com.br/dicas-e-receitas/dados-sobre-cafe-no-brasil/. Acesso em: 15 jan. 2022.
Bastiani, M., Santos, J. A. A., Schmidt, C. A P. & Sepulveda, G. P. L. (2018). Application of data mining algorithms in the management of the broiler production. Geintec. 8(4), 4574-4587. https://doi.org/10.7198/geintec.v8i4.1275.
Cankurt, S. & Subasi, A. (2015). Comparasion of linear regression and neural network models forecasting tourist arrivals to turkey. Eurasian Journal of Science &Engineering.
CEPEA (2022). Indicador do café arábica. https://www.cepea.esalq.usp.br/br/indicador/cafe.aspx.
Deina, C. et al. (2021). A methodology for coffee price forecasting based on extreme learning machines. Information Processing in Agriculture. https://doi.org/10.1016/j.inpa.2021.07.003.
Faria, T. A. (2011). Mercado future do café: um estudo de caso. Revista de Estudos Sociais, 13(26), 138-156.
Faria, A. C. S. & Manolescu, F. M. K. (2004) A produção de café no Brasil. <http://www.inicepg.univap.br/cd/INIC_2004/trabalhos/inic/pdf/IC6-8.pdf>.
Fazard, A. & Gulliver, T. A. (2019). Log message anomaly detection and classification using Auto-B/LSTM and Auto-GRU. ResearchGate.
Gazzola, M. G. (2017). Um método para avaliação automática da qualidade de recursos educacionais abertos usando deep learning. < http://www.br-ie.org/pub/index.php/sbie/article/view/7678/5473>.
Graves A. & Jaitly, N. (2014). Towards end-to-end speech recognition with recurrent neural networks. < http://proceedings.mlr.press/v32/graves14.pdf>.
Graves, A. & Schmidhuber, J. (2009). Offline handwriting recognition with multidimensional recurrent neural networks. Advances in Neural Information Processing Systems, 545–552.
Haykin, S. (2005). Neural networks: a comprehensive foundation. New Delhi: Pearson Prentice Hall.
Lawal, A. (2021). Wind speed prediction using hybrid 1D CNN and BLSTM network. IEEE Acess, 9(1). https://doi.org/10.1109/ACCESS.2021.3129883.
Lopes, L. P. (2018). Predição do preço do café naturais brasileiro por meio de modelos de statistical machine learning. Sigmae, 7(1), 1-16.
Lu, W., Li, J., Li, Y., Sun, A. & Wang, J. (2020). A CNN-LSTM-based model to forecast stock prices. Complexity. https://doi.org/10.1155/2020/6622927.
Martins, L. S. F. (2021). Análise da previsão do cenário de produção e cultivo do café arábica no Brasil. Trabalho de Conclusão de Curso. Medianeira, PR, UTFPR.
Marujo, L. (2021). Estudo comparativo entre métodos estatísticos e de inteligência artificial para previsão do preço do café no Brasil. Dissertação de mestrado. Medianeira, PR, UTFPR.
Mousa, A. E. & Schuller, B. (2016). Deep bidirectional long short-term memory recurrent neural etworks for grapheme-to-phoneme conversion utilizing complex many-to-many alignments. In: Interspeech 2016, San Francisco, USA.
Nelson, M. Q., Pereira, A C. M. & Oliveira R. A. (2017). Stock market’s price prediction with LSTM neural networks. In: International Joint Conference of Neural Networks (IJCNN), Anchorage, Alaska.
Novanda R. R. et al. (2018). A comparison of various forecasting techniques for coffee prices. https://iopscience.iop.org/article/10.1088/1742-6596/1114/1/012119/pdf.
Pacheco, A. G. C. (2016). Classificação de espécies de peixe utilizando redes neurais convolucional. https://arxiv.org/pdf/1905.03642.pdf.
Pinheiro, T. C., Santos, J. A. A. & Pasa, L. A. (2020). Gestão da produção de frangos de corte por meio de redes neurais. Revista Holos, 2(1), 1-15. https://doi.org/10.15628/holos.2020.9043.
Santos, J. A. A. (2021). Aplicação de redes neurais artificiais na previsão do preço do milho no estado do Paraná. Revista Engenharia e Tecnologia, 13(2), 124-134.
Santos, J. A. A. & Chaucoski, Y. (2020). Previsão do consumo de energia elétrica na região sudeste: um estudo de caso usando SARIMA e LSTM. Revista CEREUS, 12(1). https://doi.org/10.18605/2175-7275/cereus.v12n4p93-104.
Santos, J. A. A. & Spancerski, J. S. (2021). Previsão da produtividade de arroz: uma aplicação de redes neurais recorrentes LSTM. Revista CEREUS, 13(2), 163-175. https://doi.org/10.18605/2175-7275/cereus.v13n2p163-175.
Silva, C. A. G. (2018). Previsão do preço da commodity café arábica: Uma aplicação da Metodologia Box-Jenkins. Revista Espacios, 30(4).
SINDICAFÉ-MG (2022). O café no mundo. http://sindicafe-mg.com.br/cafe-no-mundo.
Sun, Q., Jankovic, M. V. & Bally, L. (2018). Predicting blood glucose with an LSTM and Bi-LSTM based deep neural network. https://arxiv.org/abs/1809.03817. Acesso em: 25 set. 2021.
.
Tatagiba, S. D., Pezzopane, J. E. & Reis, E. F. (2010). Crescimento vegetativo de mudas de café arábica submetidas a diferentes níveis de sombreamento. Coffee Science, 5(3): 251-261.
Zao, Z. (2017). LSTM network: a deep learning approach for short-term traffic forecast. IET Intelligent Transport Systems. 11(2), 68-75. https://doi.org/10.1049/iet-its.2016.0208.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 José Airton Azevedo dos Santos
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
