Predicting the Direction of Gold Price Returns: Integrating Composite Artificial Neural Network Models by Markov Chain Process

Year 2013, Volume: 17 Issue: 2, 15 - 28, 01.12.2013

Süleyman Bilgin Kılıç

Abstract

In this study, we first modeled daily gold returns as the discrete state Markov chain process, and second we trained an Artificial Neural Network (ANN) model in order to estimate direction of gold return. The trained model provides valuable information about the direction of next day return.

Keywords

Gold price returns, Artificial Neural Network Model, Markov process

Altın Fiyatına ait Getiri Yönünün Tahmini: Bileşik Yapay Sinir Ağları Yöntemi ile Markov Zincirleri Sürecinin Bütünleştirilmesi

Abstract

Bu çalışmada, öncelikle günlük ortalama altın fiyatına ait getiriler Markov zincirleri olarak modellenmiş ve daha sonra bir sonraki gün için getirinin yönünü tahmin eden Yapay Sinir Ağı Modelleri tahmin edilmiştir. Tahmin edilen modeller bir sonraki güne ait getirinin yönü konusunda önemli bilgiler vermektedir.

Keywords

Altın Fiyatına Ait Getiriler, Yapay Sinir Ağı Modeli, Markov Süreci

References

• Askari, M. & Askari, H. (2011), Time Series Grey System Prediction-based Models: Gold Price Forecasting, Trends in Applied Sciences Research, Vol. 6 Iss.11, pp1287-1292.
• Ismail, Z., Yahya, A. and Shabri, A. (2009), Forecasting Gold Prices Using Multiple Linear Regression Method. American Journal of Applied Sciences, Vol. 6-8, pp. 1509-1514.
• Kılıç, S.B. (2013), “Integrating Artificial Neural Network Models by Markov Chain Process: Forecasting the Movement Direction of Turkish Lira/US Dollar Exchange Rate Returns”, 14th International Symposium on Econometrics Operations Research and Statistic-(ISEOS), Sarajevo,Bosnia-Herzegovina.
• Mirmirani, S. & Li, H.C. (2004), Gold Price, Neural Networks and Genetic Algorithm, Computational Economics, vol. 23, iss. 2, pp. 193-200.
• Miswan, N.H., Ping, P.Y. and Ahmad, M.H (2013), On parameter estimation for malaysian gold prices modeling and forecasting, International Journal of Mathematical Analysis, 7(21-24), pp 1059-1068.
• Parisi, A., Parisi, F. and Díaz, D. (2008). Forecasting gold price changes: Rolling and recursive neural network models, Journal of Multinational Financial Management, Issue Vol. 18, 5, Dec., pp.477-487.
• Xu, G. ( 2011), China gold futures price prediction model - From the perspective of the gray prediction, 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce, AIMSEC 2011, August 8-10, China – Proceedings, Pages 5479-5482.
• Xu, L-P. & Luo, M-Zo (2011), Short-term Analysis and Prediction of Gold Price Based on ARIMA Model, Finance and Economics, Vol. 2011 Issue 1, pp 26-34.
• Yazdani-Chamzini, A., Yakhchali, S.H., Volungeviciene, D. and Zavadskas (2012), Forecasting gold price changes by using adaptive network fuzzy inference system, Journal of Business Economics and Management, Nov.,13; 5; pp 994- 1010.
• Zhou, S., Lai, K.K. and Yen, J. (2012) A dynamic meta-learning rate-based model for gold market forecasting, Expert Systems with Applications, Vol. 39, Issue 6, PP. 6168-6173.