HAM PETROL FİYATLARININ YAPAY SİNİR AĞLARI İLE TAHMİNİ

Abstract

Ekonomide hemen her sektör, doğrudan ya da dolaylı olarak petrole bağımlıdır. Bu nedenle petrol piyasasında ve dolayısıyla fiyatında ortaya çıkan değişiklikler, oluşturdukları zincirleme reaksiyonlar aracılığı ile hem ülke, hem de dünya ekonomisi üzerinde çeşitli etkiler yaratmaktadır. Karmaşık dinamiklerinden dolayı, oldukça değişken ve etkileşimli bir yapıya sahip petrol piyasasında geleceğe yönelik etkili planlar yapmak için doğru ve güvenilir tahminlere gereksinim vardır. Bu amaçla çalışmamızda ham petrol fiyatlarını tahmin etmek için klasik zaman serileri analiz yöntemlerinden ARIMA ile veri seti içerisindeki karmaşık ilişkileri başarıyla modelleyebilen son yıllarda zaman serisi analizinde sıkça yer alan MLP ve RBF yapay sinir ağları kullanılmıştır

Keywords

• YSA, MLP, RBF, ARIMA, Ham Petrol, Tahmin

CRUDE OIL PRICE FORECASTING WITH ARTIFICIAL NEURAL NETWORKS

Abstract

Almost every sector in economy is connected with oil directly or indirectly. Consequently, the changes on petrol industry, and thus, on petrol prices create various effects on both country and world economy by means of chaining reactions turning up. For making affective plans for the future about petrol industry which has a considerably unsteady and interactive structure because of its complex dynamics, straight and confidential predictions are needed. So, classical time series analysis method ARIMA and MLP and RBF Neural Networks which are able to model complex relationships in data set and have a large part in time series analysis recently are used in this study

Keywords

• ANN, MLP, RBF, ARIMA, Crude oil, Forecasting

References

1. Abosedra, S. ve Baghetani, H., “On The Predictive Accuracy of Crude Oil Futures Prices”, Energy Policy, Volume:32, 2004.
2. Aklin, K. ve Atman, S., Küresel Petrol Stratejilerinin Jeopolitik Açıdan Dünya ve Türkiye Üzerindeki Etkileri, İstanbul: İstanbul Ticaret Odası, Yayın-No:2006-48,
3. Alexandridis A., Livanis E, "Forecasting Crude Oil Prices Using Wavelet Neural Networks".In the proc. of 5th FSDET, Athens, Greece, 8 May, 2008.
4. Amin-Naseri, M. R. ve Gharacheh, E. A.,“A hybrid artificial intelligence approach to monthly forecasting oil price time series”. Proceedings of EANN, 2007.
5. Bernabe, A. ve diğerleri, “A Multi-Model Approach for Describing Crude Oil Price Dynamics”, Physica A, Volume:338, 2004.
6. Bianchini, M., Frasconi, P. & Gori, M. (1995) Learning without local minima in radial basis function networks. IEEE Trans. Neural Networks 6(3), s.749-755.
7. Broomhead DS, Lowe D.(1988), “Multivariable functional interpolation and adaptive Networks”, Complex Systems 2: s.321–355.
8. Chatfıeld C.,(2003),The analysis of time series: an introduction, CRC Pres

9. Chen, S., Cowan, C. F. N., Grant, P. M. (1991), “Orthogonal least squares learning algorithm for radial basis function networks.”, IEEE Trans. Neural Networks 2(2), s.302-309.
10. Cybenko G. (1989), “Approximation by superpositions of a sigmoidal function.
11. Mathematical Control Signals Systems” 2: s.303–314. Fausett, L.(1994), Fundamentals of Neural Networks: Architectures, Algorithms and Applications, Prentice Hall.
12. Fernandez, V., “Forecasting commodity prices by classification methods: The cases of crude oil andnatural gas spot prices”, Banco Central De Chile Conference, July 27, 2007.
13. Franses P. H.(1996),Periodicity And Stochastic Trends in Economic Time
14. Series, Oxford University Press Frechtling D. C.(1996), Practical Tourism Forecasting, Elsevier
15. Ghaffarı, A. ve Zare, S., “A Novel Algorithm For Prediction Of Crude Oil Price Variation Based On Soft Computing”, Energy Economics, Volume:31, 2009.
16. Harrald, P. G. ve Kamstra, M., “Evolving Artificial Neural Networks To Combine Financial Forecasts”, IEEE Transactions On Evolutionary Computation, Volume:1, No:1, 1997.
17. Haykin, S.( 1999),Neural Networks - A Comprehensive Foundation, Prentice Hall.
18. Hornik K, Stinchcombe M, White H.(1989). “Multilayer feedforward networks are universal approximators.”, Neural Networks 2: s.359–366.
19. Hornik K. (1991), “Approximation capability of multilayer feedforward networks.” ,Neural Networks 4: s.251–257.
20. Kaboudan, M. A., “Compumetric Forecasting Of Crude Oil Prices”, Proceedings of The 2001 Congress on Evolutioanry Computation, Volume:1, 2001.
21. Kulkarni, S. ve Haidar, I., “Forecasting Model For Crude Oil Price Using Artificial Neural Networks And Commodity Futures Prices”, International Journal of Computer Science and Information Security, Volume:2, No:1, 2009.
22. Kuvulmaz J., Usanmaz S., Engin S. N.(2005), “Time-Series Forecasting by
23. Means of Linear and Nonlinear Models.”, MICAI 2005, s.504-513
24. Moody, J. & Darken, C. J. (1989), “Fast learning in networks of locally-tunes processing units.” ,Neural Computation 1(2), s.281-294.
25. Öztemel, E.(2003),Yapay Sinir Ağları, Papatya Yayıncılık, İstanbul.
26. Pan, H., Haidar, I. ve Kulkarni, S., “Daily Prediction Of Short Term Trends Of Crude Oil Prices Using Neural Networks Exploiting Multimarket Dynamics”, Front. Comput. Sci., Volume:3, No:2, 2009.
27. Park, J. ve Sandberg,I.W.(1991),” Universal approximations using Radial-Basis
28. Function Network.”, Neural Computation 3(2), s.246-257
29. Powell MJD.(1987),”Radial basis functions for multivariable interpolation: a review. In Algorithms for Approximation”, Mason JC, Cox MG (eds.) Carendon Press: Oxford; s.143–167.
30. Tang, Z, Fishwick, P.A.(1993),”Feedforward neural nets as models for time series forecasting”,ORSA Journal on Computing, Vol. 5 (4), s.374–385.
31. Uğurlu, E. ve Ünsal, A., “Ham Petrol İthalatı ve Ekonomik Büyüme: Türkiye”, Ekonometri ve İstatistik Sempozyumu‟na sunulan bildiri, Erzurum 27-29 Mayıs 2009.
32. Xıe, W. ve diğerleri, "A New Method for Crude Oil Price Forecasting Based on Support Vector Machines", Lecture Notes in Computer Science, Volume:3994,
33. Zhang, G., Patuwo, B. E. ve Hu, M. Y. (1998) “Forecasting with artificial neural networks: the state of the art”, International Journal of Forecasting, 14, s.35-62.