Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Machine learning predictive modeling of the price of cassava derivative (GARRI) in the South West Of Nigeria

Treść / Zawartość
Warianty tytułu
Języki publikacji
Fluctuation in prices of Agricultural products is inevitable in developing countries faced with economic depression and this, has brought a lot of inadequacies in the preparation of Government financial budget. Consumers and producers are poorly affected because they cannot take appropriate decision at the right time. In this study, Machine Learning(ML) predictive modeling is being implemented using the MATLAB Toolbox to predict the price of cassava derivatives (garri) in the South Western part of Nigeria. The model predicted that by the year 2020, all things being equal, the price of (1kg) of garri will be 500. This will boost the Agricultural sector and the economy of the nation.
  • Department of Computer Science, Emmanuel Alayande College of Education, Oyo
  • Department of Computer Science, Federal Polytechnic, Ilaro
  • 1. Ernest, A. F. (2002). Commodity future price prediction; An Artificial Intelligence approach. A Thesis Submitted to the Graduate Faculty of the University of Georgia for the Award of Maters of Science.
  • 2. Ethem, A. (2010). Introduction to Machine Learning, second edition. London, England: The MIT Press, Cambridge, Massachusetts.
  • 3. Faisal, A., & Wumi, I. (2005). Predicting crude oil price trends using ANN modelling approach. In 25th North America Conference. Denver and Co.
  • 4. Gurudeo, T. A., & Tereq, S. (2016). Oil price forecasting based on various univariate time series models. American Journal of Operation Research, 6, 226–235.
  • 5. Harrington, P. (2012). Machine Leaning in action. Shelter Island, NY: Manning Publication Co.
  • 6. Hetemäki, L., & Mikkola, J. (2005). Forecasting Germany’s printing and writing paper imports. Forest Science, 51, 483–497.
  • 7. Iwayan, A., Muhamad, S., Andril, K., & Yunindri, W. (2010). Determination of cocoa bean quality with image processing and Artificial Neural Network. Computer Based Data Acquisition and Control in Agriculture, 2(1), 13–16.
  • 8. Izekor, O. B., Alufohai, G. O., & Eronmwon, I. (2016). Analysis of market integration and price variation in Garri marketing in Edo State, Nigeria. Nigerian Journal of Agriculture, Food and Environment, 12(4), 123–130.
  • 9. Obe, O. O., & Shangodoyin D. K. (2010). ANN based model for forecasting sugarcane production. Science Publication, Journal of Computer Science, 6(4), 439–445.
  • 10. Olagunju, F. I., Babatunde, R. O., & Salimonu, K. K. (2012). Market structure, conduct and perfor-mance of Garri processing industry in South Western, Nigeria. European Journal of Business and Management, 4(2), 99–112.
  • 11. Olanloye, D. O. (2017). Development of Artificial Intelligence Goeinformatics System for solid mineral prospecting (doctoral dissertation). Dept. of Computer Science, Nnamdi Azikiwe University, Awka, Nigeria.
  • 12. Orewa, S. A., & Egware, R. A. (2012). Vomparative analysis of rural and urban market prices for Garri in Edo State, Nigeria: Implications for Food Security. Journal of Development and Agri-cultural Economics, 4(9), 252–257.
  • 13. Peralta, J., Li, X. D., Gutierrez, G., & Sanchis, A. (2010). Time series forecasting by evolving Artificial Neural Networks using Genetic Algorithms and differential evolution. In The 2010 International Joint Conference on Neural Networks (pp. 1–8). Barcelona: IEEE. doi: 10.1109/IJCNN.2010.5596901
  • 14. Smith, V. (2010). Application of Neural Network in weather prediction.”The Pacesetter”, 10(3), 25–35.
  • 15. Sunday, B., Ini-mfon, V., Samuel, J., & Udoro, J. U. (2014). Monthly price analysis of Cassava Derivatives in Rural and Urban Market in Akwa Ibom State, Southern Nigeria. Agricultural Science Value, 2(1), 48–68.
  • 16. Wei-lun, C. (2011). Machine Learning tutorial. Disp Lab, Graduate Institute of Communication Engineering, National Taiwan University.
Typ dokumentu
Identyfikator YADDA
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.