Comparing Accuracy Performance of ELM, ARMA and ARMA-GARCH Model In Predicting Exchange Rate Return

Year 2017, , 1 - 14, 30.06.2017

Nimet Melis Esenyel , Melda Akın

https://doi.org/10.17093/alphanumeric.298658

Cited By: 2

Abstract

GARCH type models and artificial intelligence models are frequently used in the modeling of financial time series returns. In this study, the performance of ARMA and ARMA-GARCH models was compared with ELM. Four error measurement criteria were used in the performance comparison. According to the findings, ELM models of Euro and GBP exchange rates returns are superior to the ARMA and ARMA-GARCH models. According to this result, it can be said that ELM, one of the artificial intelligence-based methods, is more suitable for estimating the exchange rate returns during the period covered.

Keywords

ARMA, Artificial Neural Networks, Extreme Learning Machine, ARMA-GARCH

Döviz Kuru Getirisinin Tahmininde ELM, ARMA ve ARMA-GARCH Modellerinin Doğruluk Performansının Karşılaştırılması

Abstract

Finansal zaman serilerinin getirilerinin modellenmesinde GARCH tipi modeller ve yapay zeka modelleri sıklıkla kullanılmaktadır. Bu çalışmada ARMA ve ARMA-GARCH modellerinin performansı, yapay zeka tekniklerinden ELM ile karşılaştırılmıştır. Performans karşılaştırmada dört adet hata ölçüm kriterinden yararlanılmıştır. Elde edilen bulgulara göre Euro ve GBP döviz kurlarının ELM modellerinin, ARMA ve ARMA-GARCH modellerine kıyasla daha üstün olduğu görülmüştür. Bu sonuca göre ele alınan dönem içerisinde, döviz kuru getirilerinin tahmininde ELM’ nin daha uygun olduğu söylenebilir

Keywords

ARMA, Yapay Sinir Ağları, ELM (Hızlı Öğrenen Makina), ARMA-GARCH

References

• Huang, G.-B., & Babri, H. A. (1998). Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions. IEEE Transactions on Neural Networks, 9(1), 224–229.
• Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2004). Extreme learning machine: a new learning scheme of feedforward neural networks. In 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541) (Vol. 2, pp. 985–990 vol.2).
• Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70(1), 489–501.
• Huang, W., Lai, K. K., Nakamori, Y., & Wang, S. (2004). Forecasting Foreign Exchange Rates with Artificial Neural Networks - A Review. International Journal of Information Technology & Decision Making, 3(1), 145–165.
• Judge, G. G., Hill, R. C., Griffiths, W., Lutkepohl, H., & Lee, T. C. (1988). Introduction to the Theory and Practice of Econometrics.
• McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics, 5(4), 115–133.
• Nelson, D. B., & Cao, C. Q. (1992). Inequality Constraints in the Univariate GARCH Model. Journal of Business & Economic Statistics, 10(2), 229–235.
• Öztemel, E. (2006). Yapay Sinir Ağları (3. Baskı). İstanbul: Papatya Yayıncılık.
• Package, T., Gosso, A. A., & Training, D. (2015). Package “ elmNN .”
• Pham, H. T., & Yang, B. S. (2010). Estimation and forecasting of machine health condition using ARMA/GARCH model. Mechanical Systems and Signal Processing, 24(2), 546–558.