BORSA ENDEKSİ HAREKETLERİNİN MAKİNE ÖĞRENME ALGORİTMALARI İLE TAHMİNİ

Finansal zaman serilerinin barındırdığı belirsizlik, kaotik hareketler yanında doğrusal olmayan dinamik yapı, tahminleri oldukça güçleştirmektedir. Borsa endekslerinin politik değişimler, ekonominin genel görünümü, yatırımcıların beklenti ve yatırım tercihleri ve diğer endekslerin hareketleri gibi birçok makroekonomik faktörden etkilenmeleri, endeks tahminlerini oldukça zor ancak bir o kadar da çekici kılmaktadır. Borsa endeksi hareketleri ve geleceğe dönük tahminler üretmede makine öğrenme algoritmalarının başarılı oldukları bilinmektedir. Bu çalışmada BIST 100 endeksi hareketlerinin yönünün tahmin edilmesi problemi ele alınmıştır. Üç farklı makine öğrenme algoritması olan yapay sinir ağları, destek vektör makineleri ve naive Bayes sınıflandırıcı algoritması kullanılmış ve performansları karşılaştırılmıştır. Borsa endeksi tahminleri için kullanılan on teknik gösterge modeller için girdi olarak kullanılmıştır. Veri seti 2009-2018 periyodunu kapsayan günlük kapanış değerlerini içermektedir. Analiz sonuçları, her üç modelin de borsa endeks hareketlerini yakalamada kullanılabilir olduğunu, yapay sinir ağı algoritmasının ise daha iyi bir sınıflandırıcı olduğunu göstermiştir.

Anahtar Kelimeler:

BIST100, yapay sinir ağları, destek vektör makineleri, naive Bayes, makine öğrenme

PREDICTING STOCK MARKET MOVEMENT BY USING MACHINELEARNING ALGORITHM

In addition to the uncertainty and chaotic movements of the financial time series, the nonlinear dynamic structure makes the forecasts very difficult. The fact that the stock market index are affected by the political changes, the general outlook of the economy, the investors' expectations and investment preferences, and the movements of other indexes, make the index estimates quite difficult but attractive. It is known that the machine learning algorithms are successful in estimating stock index movements and their future values. In this study, the problem of forecasting the direction of BIST 100 index movements is discussed. Three different machine learning algorithms, artificial neural networks, support vector machines and naïve Bayes classifier were used and their performances were compared. Ten technical indicators were used as inputs for the models. The data set consists of ten-year daily closing price values covering the 2009-2018 period. Analysis results show that the models can be used to capture stock market index movements, whereas artificial neural network algorithm is a better classifier.

PDF

___

Abu-Mostafa, Y. S., ve Atiya, A. F. (1996). Introduction to financial forecasting. Applied Intelligence, 6(3), 205–213. http://doi.org/10.1007/BF00126626
Atsalakis, G. S., ve Valavanis, K. P. (2009). Surveying stock market forecasting techniques – Part II: Soft computing methods. Expert Systems with Applications, 36(3, Part 2), 5932–5941. http://doi.org/https://doi.org/10.1016/j.eswa.2008.07.006
Cao, L., ve Tay, F. E. H. (2001). Application of support vector machines in financial time series forecasting. Omega, 29(4), 309–317. http://doi.org/10.1016/S0305-0483(01)00026-3
Chen, A.-S., Leung, M. T., ve Daouk, H. (2003). Application of neural networks to an emerging financial market: forecasting and trading the Taiwan Stock Index. Computers & Operations Research, 30(6), 901–923. http://doi.org/https://doi.org/10.1016/S0305-0548(02)00037-0
Chen, Z., Matousek, R., ve Wanke, P. (2018). Chinese bank efficiency during the global financial crisis: A combined approach using satisficing DEA and Support Vector Machines☆. North American Journal of Economics and Finance, 43(September 2017), 71–86. http://doi.org/10.1016/j.najef.2017.10.003
Chun, S.-H., ve Kim, S. H. (2004). Data mining for financial prediction and trading: application to single and multiple markets. Expert Systems with Applications, 26(2), 131–139. http://doi.org/https://doi.org/10.1016/S0957-4174(03)00113-1
Enke, D., ve Thawornwong, S. (2005). The use of data mining and neural networks for forecasting stock market returns. Expert Systems with Applications, 29(4), 927–940. http://doi.org/https://doi.org/10.1016/j.eswa.2005.06.024
Hsu, S. H., Hsieh, J. P. A., Chih, T. C., ve Hsu, K. C. (2009). A two-stage architecture for stock price forecasting by integrating self-organizing map and support vector regression. Expert Systems with Applications, 36(4), 7947–7951. http://doi.org/10.1016/j.eswa.2008.10.065
Hua, S., ve Sun, Z. (2001). Support vector machine approach for protein subcellular localization prediction. Bioinformatics, 17(8), 721–728.
Huang, W., Nakamori, Y., ve Wang, S.-Y. (2005). Forecasting stock market movement direction with support vector machine. Computers & Operations Research, 32(10), 2513–2522. http://doi.org/https://doi.org/10.1016/j.cor.2004.03.016
Kara, Y., Acar Boyacioglu, M., ve Baykan, Ö. K. (2011). Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange. Expert Systems with Applications, 38(5), 5311–5319. http://doi.org/10.1016/j.eswa.2010.10.027
Khemchandani, R., Jayadeva, ve Chandra, S. (2009). Knowledge based proximal support vector machines. European Journal of Operational Research, 195(3), 914–923. http://doi.org/https://doi.org/10.1016/j.ejor.2007.11.023
Kim, K. J. (2003). Financial time series forecasting using support vector machines. Neurocomputing, 55(1–2), 307–319. http://doi.org/10.1016/S0925-2312(03)00372-2
Kimoto, T., Asakawa, K., Yoda, M., ve Takeoka, M. (1990). Stock market prediction system with modular neural networks. In 1990 IJCNN International Joint Conference on Neural Networks (pp. 1–6 vol.1). http://doi.org/10.1109/IJCNN.1990.137535
Kumar, M., ve Thenmozhi, M. (2005). Forecasting Stock Index Movement: A Comparison of Support Vector Machines and Random Fores. In Forest, Indian Institute of Capital Markets 9th Capital Markets Conference Paper. (pp. 1–16). http://doi.org/10.2139/ssrn.876544
Leung, M. T., Daouk, H., ve Chen, A.-S. (2000). Forecasting stock indices: a comparison of classification and level estimation models. International Journal of Forecasting, 16(2), 173–190. http://doi.org/https://doi.org/10.1016/S0169-2070(99)00048-5
Malkiel, B. G., ve Fama, E. F. (1970). Effıcient Capital Markets: A Review of Theory and Empirical Work. The Journal of Finance, 25(2), 383–417. http://doi.org/10.1111/j.1540-6261.1970.tb00518.x
Olson, D., ve Mossman, C. (2003). Neural network forecasts of Canadian stock returns using accounting ratios. International Journal of Forecasting, 19(3), 453–465. http://doi.org/https://doi.org/10.1016/S0169-2070(02)00058-4
Patel, J., Shah, S., Thakkar, P., ve Kotecha, K. (2015a). Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniques. Expert Systems with Applications, 42(1), 259–268. http://doi.org/10.1016/j.eswa.2014.07.040
Patel, J., Shah, S., Thakkar, P., ve Kotecha, K. (2015b). Predicting stock market index using fusion of machine learning techniques. Expert Systems with Applications, 42(4), 2162–2172. http://doi.org/10.1016/j.eswa.2014.10.031
Tan, T. Z., Quek, C., ve Ng, G. S. (2007). Biological Brain‐Inspired Genetic Complementary Learning for Stock Market and Bank Failure Prediction. Computational Intelligence, 23(2), 236–261. http://doi.org/10.1111/j.1467-8640.2007.00303.x
Tay, F. E. H., ve Cao, L. J. (2001). Improved financial time series forecasting by combining support vector machines with self-organizing feature map. Intelligent-Data-Analysis, 5, 339–354.
Thawornwong, S., ve Enke, D. (2004). The adaptive selection of financial and economic variables for use with artificial neural networks. Neurocomputing, 56, 205–232. http://doi.org/https://doi.org/10.1016/j.neucom.2003.05.001
Vanstone, B., ve Finnie, G. (2009). An empirical methodology for developing stockmarket trading systems using artificial neural networks. Expert Systems with Applications, 36(3, Part 2), 6668–6680. http://doi.org/https://doi.org/10.1016/j.eswa.2008.08.019
Vapnik, V. (1995). The nature of statistical learning theory. New York, NY: Springer.
Atsalakis, G. S., & Valavanis, K. P. (2009). Surveying stock market forecasting techniques – Part II: Soft computing methods. Expert Systems with Applications, 36(3, Part 2), 5932–5941. http://doi.org/https://doi.org/10.1016/j.eswa.2008.07.006
Chen, A.-S., Leung, M. T., & Daouk, H. (2003). Application of neural networks to an emerging financial market: forecasting and trading the Taiwan Stock Index. Computers & Operations Research, 30(6), 901–923. http://doi.org/https://doi.org/10.1016/S0305-0548(02)00037-0
Chun, S.-H., & Kim, S. H. (2004). Data mining for financial prediction and trading: application to single and multiple markets. Expert Systems with Applications, 26(2), 131–139. http://doi.org/https://doi.org/10.1016/S0957-4174(03)00113-1
Enke, D., & Thawornwong, S. (2005). The use of data mining and neural networks for forecasting stock market returns. Expert Systems with Applications, 29(4), 927–940. http://doi.org/https://doi.org/10.1016/j.eswa.2005.06.024
Thawornwong, S., & Enke, D. (2004). The adaptive selection of financial and economic variables for use with artificial neural networks. Neurocomputing, 56, 205–232. http://doi.org/https://doi.org/10.1016/j.neucom.2003.05.001
Vanstone, B., & Finnie, G. (2009). An empirical methodology for developing stockmarket trading systems using artificial neural networks. Expert Systems with Applications, 36(3, Part 2), 6668–6680. http://doi.org/https://doi.org/10.1016/j.eswa.2008.08.019
Zhong, X., ve Enke, D. (2017). Forecasting daily stock market return using dimensionality reduction. Expert Systems with Applications, 67, 126–139. http://doi.org/10.1016/j.eswa.2016.09.027
Xu, X., Zhou, C., ve Wang, Z. (2009). Credit scoring algorithm based on link analysis ranking with support vector machine. Expert Systems with Applications, 36(2, Part 2), 2625–2632. http://doi.org/https://doi.org/10.1016/j.eswa.2008.01.024