The International Arab Journal of Information Technology (IAJIT)


Parameter Tuning of Neural Network for Financial Time Series Forecasting

One of the most challengeable problems in pattern recognition domain is financial time series forecasting which aims to exactly estimate the cost value variations of a particular object in future. One of the best well-known financial time series prediction methods is Neural Network (NN) but it suffers from parameter tuning such as number of neuron in hidden layer, learning rate and number of periods that should be forecasted. To solve the problem, this paper proposes a new meta- heuristic-based parameter tuning scheme which is based on Harmony Search (HS). To improve the exploration and exploitation rates of HS, the control parameters of HS are adapted during the generations. Evaluation of the proposed method on several financial times series datasets shows the efficiency of the improved HS on parameter setting of NN for time series prediction.

[1] Box G. Jenkins G., Time Series Analysis: Forecasting and Control, Holden Day, 1970.

[2] Bozic J. and Babic D., “Financial Time Series Forecasting Using Hybrid Wavelet-Neural Model,” The International Arab Journal of Information Technology, vol. 15, no. 1, pp. 50- 57, 2018.

[3] Brillinger D., Time Series. Data Analysis and Theory, Holt, Rinehart and Winston Inc., 1975.

[4] Das S. and Suganthan P., “Differential Evolution: A Survey of the State-of-the-Art,” IEEE Transactions on Evolutionary Computation, vol. 15, no. 1, pp. 4-31, 2011.

[5] Gao X., Wang X., and Ovaska S., “Modified Harmony Search Methods for Uni-Modal and Multi-Modal Optimization,” in Proceedings of 8th International Conference on Hybrid Intelligent Systems, Barcelona, pp. 65-72, 2008.

[6] Geem Z., Kim J., and Loganathan G., “A New Heuristic Optimization Algorithm: Harmony Search. Simulation,” Journals SAGE, vol. 76, no. 2, pp. 60-68, 2001.

[7] Global Stock Markets, c/markets/global-stock-markets, Last Visited, 2015.

[8] Hannan E., Multiple Time Series, John Wiley and Sons, 1979.

[9] Haykin S., Neural Networks, Macmillan College Publishing Company, 1999.

[10] Holland J., “Genetic Algorithms,” Scientific American, vol. 267, no. 1, pp. 66-72, 1992.

[11] Kendall M. and Stuart A., the Advanced Theory of Statistics. Design and Analysis, and Time Series, Charles Griffin and Company, 1968.

[12] Kennedy J., Particle Swarm Optimization in Encyclopedia of Machine Learning, Springer, 2010.

[13] Mahdavi M., Fesanghary M., and Damangir E., “An Improved Harmony Search Algorithm For Solving Optimization Problems,” Applied Mathematics and Computation, vol. 188, no. 2, pp. 1567-1579, 2007. Zeinab Fallahshojaei was born in Lahijan, Iran, in 1988. He received the B.Sc. degree in Computer engineering from the Azad University of Lahijan, Iran, in 2012, and the M.Sc degree in computer engineering from Islamic Azad University of Buin Zahra, Iran in 2016. Mehdi Sadeghzadeh is currently, an assistant professor of the Department of Computer Engineering, Mahshahr Branch, Islamic Azad University. He Received B.Sc. degree in Computer engineering from the Amirkabir University of Technology, Tehran, Iran, and the M.Sc degree in Computer engineering from Tarbaiat Modarres University, Tehran, Iran, and Ph.D. degree in Computer engineering from the Islamic Azad University, Science and Research Branch, Tehran, Iran. His current research interests include data mining, soft computing, image processing and distributed systems.