Amer Alzaidi, Dimitar Kazakov
Computer Science, University of York, York YO10 5DD, United Kingdom
Abstract-This paper describes an equation discovery approach based on machine learning using LAGRAMGE as an equation discovery tool, with tw o sources of input, a dataset and model presented in context-free grammar. The approach is searching a large range of potential equations by a specific model. The parameters of the equation are fitted to find the best equations. The experi ments are illustratedwith commodity prices from the London Metal Exchange for th e period of January-October 2009. The outputs of the experiments are a lar ge number of equations; some of the equations display that the predicted prices are following the market trends in perfect patterns.
Key words-machine learning; equation discovery; LAGRAMG E; forcasting; islamic banking
Manuscript Number: 1674-8042(2010)01-0093-05
dio: 10.3969/j.issn.1674-8042.2010.01.19
References
[1] Divany, Tarek El, 2002. History of Banking: An Analysis, Proceedings of International Conference on a Stable and Just Global Monetary System. Intern ational Islamic University Malaysia.
[2] Zaidi, Nawazish Ali, 1991. Performance of banks under a non-interes t system. Journal of Islamic Banking and Finance, 8(1): 42-5 0.
[3] Skully, Michael, Kym Brown, 2006. Financial Performance of Islami c Banks. The 17th Asian Finance Association meeting. Auckland.
[4] M. Ayub, 2008. Understanding Islamic Finance. John Wiley.
[5] Amer Alzaidi, D. K., 2008. Artificial Intelligence for Islamic Banki ng. Muamalat and Islamic Finance Research, 5(1): 15.
[6] P. Langley, H. A. Simon, G. L. Bradshaw, J. M. Zythow, 1987. Scienti fic Discovery. MIT Press, Cambridge, MA.
[7] L. Todorovski, zeroski, , 1997. Declarative Bias in Eq uation Discovery. Proc. of 14t h International Conference on Machine Learning, pages 376-384.
[8] J. E. Hopcroft, J. D. Ullman, 1979. Introduction to Automata Theory, Languages and Computation. Addison-Wesley, Reading, MA.
[9] L. Todorovski, 1998. Declarative Bias in Equation Discovery. M.Sc. Thesis. Faculty of Computer and Information Science, Ljubljana, Slovenia.
[10] L. Todorovski, S. Dzeroski, B. Kompare, 1998. Modelling and predict ion of phytoplankton growth with equation discovery. Ecological Modell ing, 113: 71-81.
[11] L. Todorovski, Dˇ zeroski, Sˇ., 2001. Theory revision in equation discovery. Proc. of the 4t h Interna- tional Conference on Discovery Science, volume 2226 of LNCS, Morgan Kaufmann.
[12] Dimitar Kazakov, T.T., 2008. Equation Discovery for Macroeconomic M odel. Proceding of ICAART.
[full text view]
