Designing a smart algorithm for determining stock exchange signals by data mining
Subject Areas : Statisticspantea maleki-moghadam 1 , akbar alem-tabriz 2 , esmael najafi 3
1 - Central Tehran Branch, Islamic Azad University, Department of Industrial Engineering, Tehran, Iran
2 - Professor, Department of Industrial Management, Faculty of Management, Shahid Beheshti University, Tehran, Iran
3 - Assistant Professor, Department of Industrial Engineering, Faculty of Engineering, Islamic Azad University, Science and Research Branch, Tehran, Iran
Keywords: k-means تحلیل بازار سهام, تحلیل خوشه ای, الگوریتم, پیشبینی مالی, دادهکاوی,
Abstract :
One of the most important problems in modern finance is finding efficient ways to summarize and visualize the stock exchange market. This research proposes a smart algorithm by means of valuable big data that is generated by stock exchange market and different kinds of methodology to present a smart model.In this paper, we investigate relationships between the data and access to their latent information with an enormous amount of data which has a significant impact on the investor’s decisions. First, extracting technical indicators from different point of the charts based on two groups of stock exchanges like petrochemical and automotive during 1387 to 1396, then analyzing clusters by means of k-means algorithm and data mining methodology. The contributions of this paper are: 1. To create a model with twenty technical indicators in different stock exchange companies and industries.2. To evaluate the proposed model and finally to predict the sales signals at the maximum points which has significant performance and can be predicted with acceptable accuracy.
[1] Timmermann, A., & Granger, C. W. (2004). Efficient market hypothesis and forecasting. International Journal of forecasting, 20(1), 15-27.
[2] Fama, E. (1991). Efficient capital markets. Journal of Finance, XLVI, 1575–1617.
[3] Skabar, A., & Cloete, I. (2002). Neural networks, financial trading and the efficient markets hypothesis. Australian Computer Science Communications, 24(1), 241-249.
[4] Enke, D., & Thawornwong, S. (2005). The use of data mining and neural networks for forecasting stock market returns. Expert Systems with Applications, 29, 927–940.
[5] Kamber, J. H. A. M. (2006). Data Mining Concepts and Techniques.
[6] K. Davis, D. Patterson, Ethics of Big Data: Balancing Risk and Innovation, O’Reilly Media, 2012.
[7] Kumar, M., & Thenmozhi, M. (2006). Forecasting stock index movement: A comparison of support vector machines and random forest.
[8] Hsu, C. M. (2011). A hybrid procedure for stock price prediction by integrating self-organizing map and genetic programming. Expert Systems with Applications, 38(11), 14026-14036.
[9] Vrahatis, M. N., Boutsinas, B., Alevizos, P., & Pavlides, G. (2002). The new k-windows algorithm for improving the k-means clustering algorithm. Journal of Complexity, 18(1), 375–391.
[10] Allen, F., Karjalainen, R., (1999), using genetic algorithms to find technical trading rules, Journal of Financial Economics, 51, 245-271.
[11] Kuo, R. J., Chen, C. H., & Hwang, Y. C. (2001). An intelligent stock trading decision support system through integration of genetic algorithm based fuzzy neural network and artificial neural network. Fuzzy sets and systems, 118(1), 21-4
[12] Kuo, R. J., Liao, J. L., & Tu, C. (2005). Integration of ART2 neural network and genetic K-means algorithm for analyzing Web browsing paths in electronic commerce. Decision Support Systems, 40(2), 355–374.
[13] Padmanabhan, B., & Tuzhilin, A. (2002). Knowledge refinement based on the discovery of unexpected patterns in data mining. Decision Support Systems, 33, 309–321.
[14] S.R. Nanda, B. Mahanty, M.K. Tiwari.(2010).Clustering Indian stock market data for portfolio management.Expert Systems with Applications ,37 ,8793–8798.
[15] Haugen, R. (1997). Modern investment theory. Upper Saddle River, NJ: Prentice-Hall.
[16] Ballings, M., Van den Poel, D., Hespeels, N., & Gryp, R. (2015). Evaluating multiple classifiers for stock price direction prediction. Expert Systems with Applications, 42(20), 7046-705.
