Description
ABSTRACT
SHARE PRICE FORECASTING THROUGH DATA MINING WITH COMBINATORY EVOLUTIONARY ALGORITHMS
Sereval researches have been carried out in order to identify an accurate and reliable share price forecast through simulation, time series analysis, combination of artificial intelligence and time series analysis methods and recently combination of data mining and artificial intelligence with evolutionary optimization methods and algorithms. In this research, through CRISP process of data mining and reviewing recent held reaserches on combinatory algorithms of forecasting share price, combination of artificial neural network and evolutionary optimization algorithms opted to forecast share price. Genetic algorithm (GA), particle swarm optimization algorithm (PSO) and imperialistic competition algorithm (ICA) used to train artificial neural network (ANN) with share price time series reducted data of five chosed trading symbols. Mean Squarred Error (mse) records demonstrate that ANN trained with particle swarm optimization algorithm results more accurate and reliable forecasts in comparison with other ANN trained with other noticed evolutionary optimization algorithms. Also, inefficiency of ANN trained with backpropagation algorithm on account of weak recognition of turbulent data is challenged as an adjunct outcome.
Key words: forecasting, data mining, artificial neural network, evolutionary optimization algorithms
References:
| [1] Wu Ming-Tao, Econ Coll, “The research on stock price forecast model based on data mining of BP neural networks,” in Intelligent System Design and Engineering Applications (ISDEA), 2013. |
| [4] Debashish Das, Mohammad Shorif Uddin, “Data mining and neural network techniques in stock market prediction: A methodological review,” International journal of artificial intelligence and application, vol. 4, no. 1, pp. p117-127, Jan 2013. |
| [5] Jianfeng Li, Jun Zhai, Junfeng Guo, “Relative value mining in stock market based on fuzzy clustering method,” CCA2013, vol. ASTL Vol 17, pp. p 112-115, 2013. |
| [7] M.H.Fazel Zarandi, E.Hadavandi, I.B.Turksen, “A hybrid fuzzy intelligent agent-based system for stock price prediction,” International journal of intelligent system, vol. 00, pp. p 1-23, 2012. |
| [8] Dyckman, T., Philbrick, D., Stephan, J., “A comparison of event study methodologies using daily stock returns: A simulation approach,” Journal of Accounting Research, pp. p 1-30, 1984. |
| [9] Malkiel, Burton G., and Richard E. Quandt, “The supply of money and common stock prices: Comment,” The Journal of Finance, pp. p 921-926., 1972. |
| [10] Kaastra, I., & Boyd, M., “Designing a neural network for forecasting financial and economic time series,” Neurocomputing, pp. p 215-236., 1996. |
| [11] Rezaiedolatabadi, H., Sayadi, S., Hosseini, A., Forghani, M., & Shokhmgar, M., “Modeling and Forecasting Stock Prices Using an Artificial Neural Network and Imperialist Competitive Algorithm,” International Journal of Academic Research in Accounting, pp. p 296-3-2, 2013. |
| [18] Hagan, M. T., Demuth, H. B., Beale, M. H., Neural Network Design, Boston: Pws Pub., 1996. |
| [19] Paul J. Werbos, The Roots of Backpropagation. From Ordered Derivatives to Neural Networks and Political Forecasting, New York: John Wiley & Sons, Inc., 1994. |
| [20] J. S. Goetti, A.W. Brugh, B. A. Julstrom, “Arranging the Keyboard with a Permutaion-Coded Genetic Algorithm,” in Proc. of the 2005 SCM Symposium on Applied Computing, 2005. |
| [21] Atashpaz-Gargari, E., Lucas, C., “Imperialist competitive algorithm: an algorithm for optimization inspired by imperialistic competition,” in IEEE 2007, 2007. |
Reviews
There are no reviews yet.