Yapay sinir ağları ile borsa endeksi tahmini

Günümüzde yapay sinir ağları popüler olarak borsa endeks tahmini, iflas tahmini ya da sirket bono sınıflaması gibi bir çok finans problemine uygulanmaktadır. Çalısmalar, hisse senedi endeks değeri tahmini üzerinde olduğu kadar günlük endeks değisim yönü üzerinde de durmaktadır. Bazı uygulamalarda yapay sinir ağlarının veri kalıplarını öğrenmede kısıtlamaları olduğu belirtilmektedir. Yapay sinir ağları seçkin öğrenme yeteneğini sunmakla birlikte karmasık finansal veri nedeni ile tutarlı olmayan ve tahmin edilemeyen bir performans gösterebilmektedir. Buna ek olarak veri bazen o kadar hacimli olmaktadır ki öğrenme kalıpları çalısmayabilmektedir. Sürekli veri ve büyük çaptaki kayıtların varlığı nedeni ile gereksiz özelliklerin ayıklanması ve verinin boyutlarının azaltılması algoritmanın islem süresini kısaltmakta ve daha genellenebilir sonuçlar verebilmektedir. Türkiye’deki yapay sinir ağları çalısmaları genelde finansal basarısızlık ve iflasların tahmini için kullanılmıstır. Yurtdısında borsa endeksi tahmini konusunda çalısmalar olduğu halde Türkiye’de bu tip çalısmaların eksikliği görülmektedir. Bu makaleye konu olan çalısma ile amaçlanan ileri beslemeli yapay sinir ağları yaklasımı ile İMKB endeksinin tahmin edilebileceğinin gösterilmesidir. Türkiye Cumhuriyet Merkez Bankası ve diğer borsaların İnternet sitelerinden elde edilen 2 Temmuz 2001 ile 13 Temmuz 2006 tarihleri arasındaki veriler kullanılarak yapılan testler sonucunda İMKB endeks değerinin ileri beslemeli yapay sinir ağları ile de basarılı bir sekilde modellenebileceği görülmüstür.

Stoc market index prediction with artifial neural networks

Currently, artificial neural networks are applied to many finance problems such as stock market index prediction, bankruptcy prediction or bond classification. Studies were performed for the prediction of stock index values as well as daily direction of change in the index. In some applications it has been specified that artificial neural networks have limitations for learning the data patterns or that they may perform inconsistently and unpredictable because of the complex financial data used. Continuous data and large scale of records require the removal of unnecessary properties which decreases the data volume, algorithm runtime and help to achieve more general results. In Turkey artificial neural networks are mostly used in predicting financial failures. There has been no specific research for prediction of Turkish stock market values. The aim of this paper is to use artificial neural networks to predict Istanbul Stock Exchange (ISE) market index value. The tests are performed using the data gathered for the period of July 2, 2001 through July 13, 2006 from the websites of Central Bank of Republic of Turkey and foreign stock markets. The results have shown that feed forward artificial neural networks can also be used to model ISE market index value successfully.

___

  • AHMADİ, H., 1990, “Testability of the Arbitrage Pricing Theory by Neural Networks”, Proceedings of the International Conference on Neural Networks, s:385-393.
  • ALTAY, E., SATMAN, M. H., 2005, “Stock Market Forecasting: Artificial Neural Networks and Linear Regression Comparison in an Emerging Market”, Journal of Financial Management and Analysis, Vol:18, No:2, s:18-33.
  • BAMBANG, B., WIDODO, R.J., SUTALAKSANA, I.Z., SİNGGİH, M., 2002, “Indonesia Stock Market Prediction (SMGR/GGRM), Using Time Series Neural Networks”, Proceedings of the Sixth AEESEAP Triennial Conference, Kuta, Bali, Indonesia, August 23 – 25.
  • BAXTER, C.W., 2001, “Modelling Heuristics from Literature”, CIV E 729 Course Notes, Dept. of Civil and Environmental Engineering. University of Alberta, Edmonton, Canada, www.civil.ualberta.ca/courses/cive729 /lectures/lecture5.ppt, retrieved on 2004.
  • BROCK, W., LAKONISHOC, J., LE BARON, B., 1992, “Simple Technical Trading Rules and the Stochastic Properties of the Stock Returns”, The Journal of Finance, Vol:XLVII, No:5, s:1731-1764.
  • CARSTEN, P., THORSTEIN R., 1993, “Jetnet 3.0: A Versatile Artificial Neural Network Package”, www.thep.lu.se/pub/Preprints/93/lulutp- 93-29.ps.gz, retrieved on 2004, Sweden.
  • CHOI, J. H., LEE M. K., RHEE, M. W., 1995, “Trading S&P 500 Stock Index Futures Using a Neural Network”, The Proceedings of the Third Annual International Conference on Artificial Intelligence Applications on Wall Street, R. S. Freedman, ed., s:63-72.
  • DASH, M., LIU, H., 1997, “Feature Selection Methods for Classifications”, Intelligent Data Analysis: An International Journal, Vol:1, No:3, s:131-156.
  • DEBOECK, G. J., 1994, Trading on the Edge, John Wiley & Sons Inc., New York.
  • DİLER, A. İ., 2003, “İMKB Ulusal 100 Endeksinin Yönünün Yapay Sinir Ağları: Hata Geriye Yayma Yöntemi ile Tahmin Edilmesi”, İMKB Dergisi, No:7, s:65–81.
  • EGELİ, B., ÖZTURAN, M., & BADUR, B., 2003, Stock Market Prediction Using Artificial Neural Networks, Proceedings of the 3rd Hawaii International Conference on Business, Hawai, USA.
  • GALLANT, S.I., 1993, Neural Network Learning and Expert Systems, MIT Press, Cambridge. GENÇAY, R., 1998, “The Predictability of Security Returns with Simple Technical Trading Rules”, Journal of Emprical Finance, Vol:5. s:347-359.
  • GUNASEKARAGE, A, POWER, D. M. 2001, “The Profitability of Moving Average Trading Rules in South Asian Stock Markets”, Emerging Markets Review, Vol:2, s:17-33.
  • KAMIJO, K., TANIGAWA, T., 1990, “Stock Price Pattern Recognition: A Recurrent Neural Network Approach”, Proceedings of the International Joint Conference on Neural Networks, s:215-221.
  • KASPERKIEWICZ, J., RAEZ, J., DUBRAWSKI, A., 1995, “HPC Strength Prediction Using Artificial Neural Network”, Journal of Computing in Civil Engineering, Vol:9, No:4, s:279-284.
  • KIMOTO, T., ASAKAWA, K., YODA, M., TAKEOKA, M., 1990, “Stock Market Prediction System with Modular Neural Network”, Proceedings of the International Joint Conference on Neural Networks, s:1-6.
  • KIRKPATRICK II, DAHLQUIST, J. R., 2007, Technical Analysis : The Complete Resource for Financial Market Technicians, Imprint Upper Saddle River, N.J. : FT Press Financial Times.
  • KOHARA, K., ISHIKAWA, T., FUKUHARA, Y., NAKAMURA, Y., 1997, “Stock Price Prediction Using Prior Knowledge and Neural Networks”, International Journal of Intelligent Systems in Accounting, Finance and Management, Vol:6, No:1, s:11-22.
  • KWON, K., KISH, R. J., 2001, “A Comperative Study of Technical Trading Strategies and Return Predictability: An Extension of Brock, Lakonishok, LeBaron (1992) Using NYSE and NASDAQ Indices”, The Quarterly Review of Economics and Finance, Vol:42, s:611-631.
  • LAI, S., SERRA, M., 1997, “Concrete Strength Prediction by Means of Neural Network”, Construction and Building Materials, Vol:11, No:2, s:93-98.
  • MIZUNO, H., KOSAKA, M., YAJIMA, H., KOMODA N., 1998, “Application of Neural Network to Technical Analysis of Stock Market Prediction”, Studies in Informatic and Control, Vol:7, No:3, s:111-120.
  • MURPHY, J.J, 1999, Technical Analysis of the Financial Markets: A Comprehensive Guide to Trading Methods and Applications, Imprint New York: New York Institute of Finance..
  • NAGENDRA, S., 1998, “Practical Aspects of Using Neural Networks: Necessary Preliminary Specifications”, GE Research and Development Center Technical Paper.
  • NEHDI, M., EL CHABIB, H., EL NAGGAR, H., 2001a, “Predicting Performance of Self-Compacting Concrete Mixtures Using Artificial Neural Networks”, ACI Materials Journal, Vol:98, No:5, s:394-401.
  • NEHDI, M., DJEBBAR, Y., KHAN, A., 2001b, “Neural Network Model for Preformed-Foam Cellular Concrete”, ACI Materials Journal, Vol:98, No:5, s:402-410.
  • PARTOVI, F.Y., ANANDRAJAN, M., 2002, “Classifying Inventory Using an Artificial Neural Network Approach”, Computers and Industrial Engineering, Vol:41, s:389-404.
  • PHUA, P.K.H., MING, D., LIN, W., 2000, “Neural Network With Genetic Algorithms For Stocks Prediction”, Fifth Conference of the Association of Asian-Pacific Operations Research Societies Proceedings, 5th - 7th July, Singapore.
  • ROSENBLATT, F., 1961, Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms, Spartan Press, Washington DC.
  • RUMELHART, D.E., HINTON, G.E., WILLIAMS, R.J., 1986, “Learning Internal Representations by Error Propagation”, Parallel Distributed Processing: Explorations in the Microstructures of Cognition, Rumelhart DE., McClelland, J.L. (eds.), Vol:1, s:318-362. MIT Press, Cambridge.
  • SEXTON, R. S., DORSEY, R. E., JOHNSON, J. D., 1998, “Toward Global Optimization of Neural Networks: A Comparison of the Genetic Algorithm and Backpropagation”, Decision Support Systems, Vol:2, s:171-185.
  • SENOL, D., ÖZTURAN, M., 2008, “Stock Price Direction Prediction Using Artificial Neural Network Approach: The Case of Turkey”, Journal of Artificial Intelligence, Vol:1, No:2.
  • TANNER, C., 2005, “Accelerating Artificial Neural Network Learning via Weight Predictions”, www.cs.ucla.edu/~ctanner/papers/01_ Accelerating_NN_Learning_04_2005. pdf, retrieved on 2009.
  • TEH, C. I., WONG, K. S., GOH, A. T. C., JARITNGAM, S., 1997, “Prediction of Pile Capacity Using Neural Networks”, Journal of Computing in Civil Engineering, Vol:11, No:2, s:129-138.
  • YEH, I.C., 1998, “Modeling of Strength of High-Performance Concrete Using Artificial Neural Networks”, Cement and Concrete Research, Vol:28, No:12, s:1797- 1808.
  • YEH, I.C., 1999, “Design of High- Performance Concrete Mixture Using Neural Networks and Nonlinear Programming”, Journal of Computing in Civil Engineering, Vol:13, No:1, s:36-42.
  • YILDIZ, B., 2001, “Finansal Basarısızlığın Öngörülmesinde Yapay Sinir Ağı Kullanımı ve Halka Açık Sirketlerde Ampirik Bir Uygulama”, İMKB Dergisi, Vol:5, No:17.
  • YOON, Y., SWALES, G., 1991, “Predicting Stock Price Performance: A Neural Network Approach”, Proceedings of the 24th Annual Hawaii International Conference on System Sciences, s:156-162.
  • YUMLU, S., GÜRGEN, F., OKAY, N., 2004, “A Comparison of Global, Recurrent and Smoothed-Piecewise Neural Models for Istanbul Stock Exchange Prediction”, Pattern Recognition Letters, Vol:26, s:2903- 2103.