Agricultural commodity price prediction via machine learning algorithms

  • Sergio Nunes Ludovico Federal University of Alfenas, Brazil
  • Ricardo Menezes Salgado Federal University of Alfenas, Brazil
  • Luiz Alberto Beijo Federal University of Alfenas, Brazil
  • Eliseu Cesar Miguel Federal University of Alfenas, Brazil
  • Marcelo Lacerda Rezende Federal University of Alfenas, Brazil https://orcid.org/0000-0003-1106-4176
Keywords: Agribusiness, Forecasting commodity prices, Artificial intelligence

Abstract

The prediction of values in a time series is the object of study in several fields of knowledge. In the agricultural commodities futures market, this type of information can be used to minimize risks to investments and contribute to the increase in the volume of negotiations of various commodities. As the prices of these assets are influenced by many external variables, predictions are usually made through analysis fundamentalist or technical and this work is carried out by specialists in the field. That restricts the access of individuals who could invest, but does not do so because they do not have this knowledge that is necessary for the survival of this business on the Stock Exchanges. This article discusses computational methods, which involve the following algorithms: k-nearest neighbor; random forest; Artificial neural networks; support vector machine; and extreme gradient boosting applied to historical data for the following commodities: sugar; live cattle; coffee; ethanol; corn; and soybean with the objective of predicting prices in the horizons of one and ten steps ahead using the regression technique. The results show that the predictions of smart models have high short-term performance. In this sense, speculators and hedges can benefit by use the proposed technique as support for decision making.

References

BELL, J. Machine Learning : Hands-On for Developers and Technical Professionals, 2ª ed. Indianapolis: John Wiley & Sons, 2020.

BLOSS, M. et al. Derivativos : Guia Prático para Investidores Novatos e Experientes. Munique: Oldenbourg Wissenschaftsverlag, 2013.

BLYTH, T. S.; ROBERTSON E. F. Basic Linear Algebra , 2ª ed. London: Springer-Verlag, 2005.

BRASIL. Ministério da Economia Indústria, Comércio Exterior e Serviços. Estatísticas de Comércio Exterior . 2019. Disponível em: http://comexstat.mdic.gov.br Acesso em: 15 mai. 2020.

BRESSAN, A.A.; LIMA, J.E. Modelos de previsão de preços aplicados aos contratos futuros de boi gordo na BM &F . Nova Economia, Belo Horizonte, v.12, n.1, p.117-140, 2003.

BRINK, H.; RICHARDS J. W.; FETHEROLF M. Real-World Machine Learning . New York: Manning Publications Co., 2017.

CEPEA. Centro de Estudos Avançados em Economia Aplicada. Preços Agropecuários . 2020. Disponível em: https://www.cepea.esalq.usp.br . Acesso em: 20 mai. 2020.

CERETTA, P. S.; RIGHI, M. B.; SCHLENDER, S. G. Previsão do Preço da Soja : Uma Comparação Entre os Modelos ARIMA e Redes Neurais Artificiais. Revista Informações Econômicas, São Paulo, v.40, n.9, p.15-27, set. 2010.

CERQUEIRA, V.; et al. Arbitrated Ensemble for Time Series Forecasting . Springer International Publishing, Porto, Lecture Notes in Computer Science, v.10535, p.478?494, dez. 2017.

CORRÊA, A. L.; RAÍCES, C. Derivativos Agrícolas . Santos: Editora Comunicar, 2017.

DASQUPTA, N. Practical Big Data Analytics : Hands-on Techniques to Implement Enterprise Analytics and Machine Learning Using Hadoop, Spark, NoSQL and R. Birmingham: Packt Publishing Ltd, 2018.

DAVISON, A. C.; HINKLEY, D. V. Bootstrap Methods and Their Application . New York: Cambridge University Press, 1997.

DREW, C.; WHITE, D. M. Machine Learning for Hackers . Sebastopol: O'Reilly, 2012.

FERREIRA, L.; et al. Utilização de Redes Neurais Artificiais como Estratégia de Previsão de Preços no Contexto de Agronegócio . RAI, São Paulo, v.8, n.4, p.6-26, out./dez. 2011.

FAUZIAH, N. F., GUNARYATI, G. Comparison Forecasting with Double Exponential Smoothing and Artificial Neural Network to Predict the Price of Sugar . International Journal of Simulation - Systems Science & Technology, v. 18, n. 4, p 13.1-13.8, 2017.

GELMAN, A; HILL, J. Data Analysis Using Regression and Multilevel/Hierarchical Models . Cambridge: Cambridge University Press., 2007.

GORI, M. Machine Learning : A Constraint-Based Approach. Cambridge: Elsevier, 2018.

GRAUPE, D. Principles of Artificial Neural Networks , 3ª ed. New Jersey: World Scientific Publishing Co. Pte. Ltd., 2013.

HANSEN, L, K.; SALAMON, P.; Neural network ensembles . IEEE Trans - Pattern Anal, Machince Intell, New York, p.993-1001, oct. 1990.

HUANG, S. C.; WU, C. F; Energy Commodity Price Forecasting with Deep Multiple Kernel Learning . MDPI, Taiwan, 5 nov. 2018, Energies. p.8 e p.14.

KRAMER, O. Dimensionality Reduction with Unsupervised Nearest Neighbors . Oldenburg: Springer-Verlag, 2013.

KUMAR, A.; JAIN, M.; Ensemble Learning for AI Developers : Learn Bagging, Stacking, and Boosting Methods with Use Cases. New York: Apress, 2020.

LIMA, F. G.; et al. Previsão de Preços de Commodities com Modelos ARIMA-GARCH e Redes Neurais com Ondaletas : Velhas Tecnologias - Novos Resultados. R.Adm., São Paulo, v.45, n. 2, p.188-202, abr./maio/jun. 2010.

LOPES, L. P. Predição do Preço do Café Naturais Brasileiro por meio de Modelos de Statistical Machine Learning . Sigmae, Alfenas, v.7, n.1, p.1-16, 2018.

MIRANDA, A. P.; CORONEL, D. A.; VIEIRA, K. M. Previsão do mercado futuro do café arábica utilizando redes neurais e métodos econométricos . Revista Estudos do CEPE, 38, 66-98, 2013.

MOLERO, L.; MELLO, E. Derivativos : Negociação e Precificação, 1ª ed, São Paulo: Saint Paul Editora, 2018.

MUELLER, J. P.; MASSARON, L. Machine Learning For Dummies . Hoboken: John Wiley & Sons, Inc., 2016.

PAL, A.; PRAKASH, P. Practical Time Series Analysis : Master Time Series Data Processing, Visualization, and Modeling using Python. Birmingham: Packt Publishing, 2017.

PANESAR, A. Machine Learning and AI for Healthcare : Big Data for Improved Health Outcomes. Coventry: Apress, 2019.

PAZ, L.; BASTOS, M. Mercado Futuro : Como Vencer Operando Futuros. Rio de Janeiro: Elsevier, 2012.

PINHEIRO, C. A. O.; SENNA, V.; MATSUMOTO, A. S. Price Forecasting for Future Contracts on Agribusiness Through Neural Network and Multivariate Spectral Analysis . Gestão, Finanças e Contabilidade. Salvador, v. 6, n. 3, p. 98-124, set./dez., 2016.

PIOT-LEPETIT, I.; M'BAREK R. Methods to Analyse Agricultural Commodity Price Volatility . New York, Springer, 2011.

QUI, X; et al. Ensemble Deep Learning for Regression and Time Series Forecasting . IEEE. Cambridge, p. 1-6, 2014.

RAO, D. J. Keras to Kubernetes : The Journey of a Machine Learning Model to Production. Indianapolis: Wiley, 2019.

REIS FILHO, I. J.; et al. A Integração de Séries Temporais e Dados de Textos para a Previsão de Preços Futuros de Milho e Soja . Revista de Sistemas de Informação. v. 01, n. 01, 2020

RUSSEL, S.; NORVIG, P. Inteligência Artificial , 3ª ed. Rio de Janeiro: Elsevier, 2013.

SAMMUT, C.; WEBB, G. Encyclopedia of Machine Learning . New York: Springer, 2011.

SOBREIRO, V. A.; ARAÚJO, P. H.; NAGANO, M. S. Precificação do Etanol Utilizando Técnicas de Redes Neurais Artificiais . R.Adm, São Paulo, v.44, n.1, p.46-58, jan./fev./mar. 2009.

STALPH, P. Analysis and Design of Machine Learning Techniques : Evolutionary Solutions for Regression, Prediction, and Control Problems. Wiesbaden: Springer Vieweg, 2014.

TATTAR, P. N. Hands-On Ensemble Learning with R : A Beginner?s Guide to Combining the Power of Machine Learning Algorithms Using Ensemble Techniques. Mumbai: Packt Publishing, 2018.

WANG, J.; LI, X. A combined Neural Network Model for Commodity Price Forecasting with SSA. Soft Computing . Berlin, 22 fev. 2018, Springer-Verlag GmbH Germany, part of Springer Nature 2018, p. 5323.

WAQUIL, P. D.; MIELE, M.; SCHULTZ, G. Mercados e Comercialização de Produtos Agrícolas . Porto Alegre: Editora da UFRGS, 2010.

XIONG, T.; et al. A Combination Method for Interval Forecasting of Agricultural Commodity Futures Prices . Elsevier BV, Netherlands, 2015, Knowledge-Based Systems. p. 1-11.

ZHANG, C.; MA, Y. Ensemble Machine Learning : Methods and Applications. London: Springer, 2012.

ZHANG, P. Neural Networks in Business Forecasting . London: Idea Group Publishing, 2004.

ZHANG, Y.; NA S. A Novel Agricultural Commodity Price Forecasting Model Based on Fuzzy Information Granulation and MEA-SVM Model . Mathematical Problems in Engineering. Londres, 11 nov. 2018, v. 2018, p. 1-10.

Published
21-01-2023
Section
Data Science & Machine Learning