Using Neural Networks for Predicting Futures Contract Prices of White Maize in South Africa

ABSTRACT

The growing ability to collect and integrate data from disparate sources on a larger scale creates new opportunities for improved decision making. The concepts of using data for predictions by using statistical or computational intelligence models have been researched extensively. However, the tools and techniques that make it possible to analyse the data in real-time as it is created brings about additional opportunities for discovering useful patterns and timely actionable insights. The prices of agricultural grain commodities are known to be volatile due to several factors that influence the prices of grain commodities. Moreover, different combinations of these factors are responsible for the price volatility at different times.

This paper carries out a real-time prediction of the futures contract prices of white maize in South Africa as a case study for the use of neural networks for predictive analytics in the financial markets. The predictive analytics model implemented in this study takes into consideration the volatility of the market and the need for the model to be contextual. Relevant data from disparate sources were identified, acquired and integrated into a single source. Thereafter, an exploratory analysis was carried out to understand the relationships that exist between the acquired datasets. A predictive model for the December futures contract prices of white maize on the Johannesburg Stock Exchange (JSE) was proposed using the Back Propagation Neural Network and SAP HANA was used as the enabling technology. The proposed model was used to predict the futures contract prices of white maize on the JSE over a period of time. The validation and evaluation of the proposed model indicate that this approach can be used to predict the futures prices of white maize in South Africa and can be incorporated into a Decision Support System for relevant stakeholders.

References

1. Abbott, P.C., Hurt, C. and Tyner, W.E. 2011. What's driving food prices in 2011. Farm Foundation Issue Report.
2. Alpaydin, E. 2010. Introduction to machine learning. The MIT Press.
3. Bennett, C., Stewart, R.A. and Lu, J. 2014. Autoregressive with exogenous variables and neural network short-term load forecast models for residential low voltage distribution networks. Energies. 7, 5, 2938-- 2960.
4. Bontempi, G., Taieb, S. Ben and Le Borgne, Y.A. 2013. Machine learning strategies for time series forecasting. Business Intelligence. Springer Berlin Heidelberg. 62--77.
5. Box, G. and Jenkins, G. 1970. Time series analysis: Forecasting and control. Holden-Day.
6. Bukharov, O.E. and Bogolyubov, D.P. 2015. Development of a decision support system based on neural networks and a genetic algorithm. Expert Systems with Applications. 42, 6177--6183.
7. Chen, P.C.L. and Zhang, C.Y. 2014. Data-Intensive applications, challenges, techniques and technologies: A survey on Big Data. Information Sciences. 275, 314--347.
8. Co, H.C. and Boosarawongse, R. 2007. Forecasting Thailand's rice export: Statistical techniques vs. artificial neural networks. Computers and Industrial Engineering. 53, 4, 610--627.
9. Crone, S.F. and Kourentzes, N. 2010. Feature selection for time series prediction: A combined filter and wrapper approach for neural networks. Neurocomputing. 73, 1923--1936.
10. DAFF 2015. Economic review of the South African agriculture. Department of Agriculture, Forestry and Fisheries.
11. Dean, J. 2014. Big Data, Data Mining and Machine Learning. John Wiley.
12. Doyer, O.T., D'Haese, M.F.C., Kirsten, J.F. and Van Rooyen, C.J. 2007. Strategic focus areas and emerging trade arrangements in the South African agricultural industry since the demise of the marketing boards. Agrekon. 46, 4, 494--513.
13. Engelbrecht, A.P. 2007. Computational Intelligence: An introduction. John Wiley.
14. Evans, C., Pappas, K. and Xhafa, F. 2013. Utilizing artificial neural networks and genetic algorithms to build an algo-trading model for intra-day foreign exchange speculation. Mathematical and Computer Modelling. 58, 1249--1266.
15. Geyser, M. and Cutts, M. 2007. SAFEX maize price volatility scrutinised. Agrekon. 46, 3, 291--305.
16. Global agricultural supply and demand: Factors contributing to the recent increase in food commodity prices: 2008. http://www.ers.usda.gov/publications/wrs0801/. Accessed: 2015-03-15.
17. Goes, P.B. 2014. Big Data and IS research. MIS Quarterly. 38, 3, 3--8.
18. Headey, D. and Fan, S. 2008. Anatomy of a crisis: The causes and consequences of surging food prices. Agricultural Economics. 39, 1, 375--391.
19. Hevner, A.R. 2007. A three cycle view of design science research. Scandinavian Journal of Information Systems. 19, 2, 87--92.
20. Irwin, S.H., Sanders, D.R. and Merrin, R.P. 2009. Devil or Angel? The role of speculation in the recent commodity price boom (and bust). Journal of Agricultural and Applied Economics. 41, 2, 377--391.
21. Jabjone, S. and Wannasang, S. 2014. Decision support system using artificial neural network to predict rice production in Phimai district, Thailand. International Journal of Computer and Electrical Engineering. 6, 2, 162--166.
22. Johannesson, P. and Perjons, E. 2012. A design science primer. Lexington.
23. Jordaan, H. and Grové, B. 2010. Factors affecting forward pricing behaviour: Implications of alternative regression model specifications. South African Journal of Economic and Management Sciences. 13, 2, 113--122.
24. Kaastra, I. and Boyd, M. 1996. Designing a neural network for forecasting financial and economic time series. Neurocomputing. 10, 215--236.
25. Khamis, A., Nabilah, S. and Binti, S. 2014. Forecasting wheat price using Backpropagation and NARX Neural Network. The International Journal of Engineering and Science. 3, 11, 19--26.
26. Khashei, M. and Bijari, M. 2011. A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Applied Soft Computing Journal. 11, 2, 2664--2675.
27. Khashei, M. and Bijari, M. 2010. An artificial neural network (p, d, q) model for time series forecasting. Expert Systems with Applications. 37, 1, 479--489.
28. Khashei, M. and Bijari, M. 2010. An artificial neural network (p, d, q) model for timeseries forecasting. Expert Systems with Applications. 37, 1, 479--489.
29. Lantz, B. 2013. Machine Learning with R. Packt Publishing.
30. Larose, D.T. 2005. Discovering knowledge in data: An introduction to data mining. John Wiley.
31. Minelli, M., Chambers, M. and Dhiraj, A. 2013. Big Data, big analytics. John Wiley.
32. Mofokeng, M. and Vink, N. 2013. Factors affecting the hedging decision of maize farmers in Gauteng province. Fouth International Conference of the African Association of Agricultural Economists (Hammemet, 2013).
33. O'Neil, C. and Schutt, R. 2014. Doing Data Science. O'Reilly Media.
34. Peffers, K., Tuunanen, T., Rothenberger, M.A. and Chatterjee, S. 2008. A Design Science Research methodology for Information Systems research. Journal of Management Information Systems. 24, 3, 45--77.
35. Phillips-Wren, G., Mora, M., Forgionne, G.A. and Gupta, J.N. 2009. An integrative evaluation framework for intelligent decision support systems. European Journal of Operational Research. 195, 642--652.
36. Provost, F. and Fawcett, T. 2013. Data Science for business. O'Reilly Media.
37. Qi, M. and Zhang, G.P. 2008. Trend time series modeling and forecasting with neural networks. IEEE Transactions on Neural Networks. 19, 5, 808--816.
38. Ruta, D. 2014. Automated trading with machine learning on Big Data. 2014 IEEE International Congress on Big Data (Anchorage, 2014).
39. Sauter, V.L. 2010. Decision Support Systems for Business Intelligence. John Wiley.
40. Shmueli, G. and Koppius, O. 2010. Predictive analytics in Information Systems research.
41. Shumway, R.H. and Stoffer, D.S. 2011. Time series analysis and its applications. Springer Science + Business Media.
42. Trostle, R. 2008. Fluctuating food commodity prices: A complex issue with no easy answers. Economic Research Service/USDA.
43. Tsadiras, A.K., Papadopoulos, C.T. and O'Kelly, M.E.J. 2013. An artificial neural network based decision support system for solving the buffer allocation problem in reliable production lines. Computers & Industrial Engineering. 66, 4, 1150--1162.
44. Tsay, R.S. 2010. Analysis of financial time series. John Wiley.
45. Vaishnavi, V.K. and Kuechler, W. 2015. Design science research methods and patterns: Innovating information and communication technology. Taylor and Francis Group.
46. Venter, M.M., Strydom, D.B. and Grové, B. 2013. Stochastic efficiency analysis of alternative basic grain marketing strategies. Agrekon. 52, 46--63.
47. Wiles, P.S. and Enke, D. 2014. Nonlinear modeling using Neural Networks for trading the soybean complex. Procedia Computer Science. 36, 234--239.
48. Wright, B.D. 2011. The economics of grain price volatility. Applied Economic Perspectives and Policy. 33, 1, 32--58.
49. Yu, S. and Ou, J. 2009. Forecasting model of agricultural products prices in wholesale markets based on combined BP neural network-time series model. International Conference on Information Management, Innovation Management and Industrial Engineering, 558--561.
50. Zhang, G.P. 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing. 50, 159--175.
51. Zou, H.F., Xia, G.P., Yang, F.T. and Wang, H.Y. 2007. An investigation and comparison of artificial neural network and time series models for Chinese food grain price forecasting. Neurocomputing. 70, 2913--2923.