PREDICTION OF STOCK MARKET INDEX DIRECTION WITH TREE-BASED ENSEMBLE MACHINE LEARNING METHODS: THE CASE OF BIST-100

Öz

The establishment of an effective prediction model for the direction of stock market indices is quite challenging due to the complex and non-stationary nature of financial data. Predicting the upward or downward movements of the stock market index, especially in emerging market exchanges where the impacts of external factors and shocks are observed more deeply, is of significant importance to stakeholders such as investors, governments, financial institutions, and creditors, as well as researchers. The aim of this study is to predict the direction of the stock market index with tree-based ensemble Machine Learning (ML) methods. Technical Indicators calculated after applying Exponential Smoothing to daily Opening, Closing, Highest, Lowest and Volume data of three years were considered as input variables of the model. In addition, the input variable space was expanded by increasing the window lengths of the Technical Indicators. In the study, Random Forest, XGBoost and CatBoost methods,which based on Decision Trees, are used as ensemble ML methods. Bayesian Search was employed to determine the optimal parameters. According to the findings of the study, all selected methods demonstrated accuracy rates ranging from 89.7% to 90.4%, and considering other performance evaluation criterias, XGBoost was identified as the best prediction method.

Anahtar Kelimeler

• Ensemble Machine Learning
• Tecnical Indicators
• Stock Market Way Prediction
• Random Forest
• XGBoost
• CatBoost

BORSA ENDEKS YÖNÜNÜN AĞAÇ TABANLI TOPLULUK MAKİNE ÖĞRENMESİ YÖNTEMLERİ İLE TAHMİNİ: BİST-100 ÖRNEĞİ

Öz

Borsa endeks yönünün tahmininde finansal verilerin karmaşık ve durağan olmayan yapısı nedeniyle etkin bir tahmin modelinin kurulması oldukça zordur. Bazı dışsal faktörlerin ve şokların etkilerinin daha derin gözlendiği gelişmekte olan ülke borsalarında, borsa endeksinin aşağı veya yukarı yönlü hareketini tahmin etmek gerek yatırımcılar, hükümetler, finansal kurumlar ve kreditörler gibi paydaşlar gerekse de araştırmacılar için önemli bir konudur. Bu çalışmanın amacı, Borsa İstanbul 100 (BİST-100) endeksinin borsa endeksinin yönünü ağaç tabanlı topluluk Makine Öğrenmesi (ML) yöntemleriyle tahmin etmektir. Üç yılın günlük Açılış, Kapanış, En Yüksek, En Düşük ve Hacim verilerine Üstel Düzgünleştirme uygulandıktan sonra hesaplanan Teknik Göstergeler modelin girdi değişkenleri olarak ele alınmıştır. Ayrıca Teknik Göstergelerin pencere uzunlukları artırılarak girdi değişkeni uzayı genişletilmiştir. Çalışmada Karar Ağaçlarına dayanan topluluk makine öğrenmesi yöntemlerinden Random Forest, XGBoost ve CatBoost kullanılmıştır. Modelin parametreleri Bayesyan Arama (Bayesian Search) yöntemi ile optimize edilmiştir. Çalışmanın bulgularına göre, tercih edilen bütün yöntemler %89,7 ile %90,4 aralığında doğruluk oranına sahipken ve diğer performans değerlendirme kriterleri de dikkate alındığında en iyi performansa sahip yöntemin XGBoost olduğu görülmektedir.

Anahtar Kelimeler

• Topluluk Makine Öğrenmesi
• Teknik Göstergeler
• Borsa Yönü Tahmini
• Rassal Orman
• XGBoost
• CatBoost

Kaynakça

1. Aras, S. (2020). Using technical indicators to predict stock price index movements by machine learning techniques, E. Sarikaya (Ed.), In Theory and Research in Social, Human and Administrative Sciences II, (1. Baskı, s. 249-274) içinde. Gece Publishing
2. 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), 7046-7056. Basak, S., Kar, S., Saha, S., Khaidem, L., & Dey, S. R. (2019). Predicting the direction of stock market prices using tree-based classifiers. The North American Journal of Economics and Finance, 47, 552-567.
3. Breiman, L., Friedman, J.H., Olshen, R., & Stone, A.C.G. (1984). Classification and Regression Trees (1). Wadsworth International Group, Belmont, California, USA.
4. Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
5. Chen, H. Y., Lee, C. F., & Shih, W. K. (2016). Technical, fundamental, and combined information for separating winners from losers. Pacific-Basin Finance Journal, 39, 224-242. https://doi.org/10.1016/j.pacfin.2016.06.008
6. Tay, F. E., & Cao, L. (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
7. Cao, J., Li, Z., & Li, J. (2019). Financial time series forecasting model based on CEEMDAN and LSTM. Physica A: Statistical mechanics and its applications, 519, 127-139. https://doi.org/10.1016/j.physa.2018.11.061
8. Cavalcante, R. C., Brasileiro, R. C., Souza, V. L., Nobrega, J. P., & Oliveira, A. L. (2016). Computational intelligence and financial markets: A survey and future directions. Expert Systems with Applications, 55, 194-211. https://doi.org/10.1016/j.eswa.2016.02.006.

9. Chen, T., & Guestrin, C. (2016, August, 13-17). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining [Oral presentation]. San Francisco, California, USA
10. Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., ... & Li, Y. (2019). Xgboost: extreme gradient boosting. R package version 0.90. 0.2. R Package Version 0.90. 0.2.
11. Dai, Y., & Zhang, Y. (2013). Machine learning in stock price trend forecasting. Stanford University, http://cs229. stanford. edu/proj2013/DaiZhang-MachineLearningInStockPriceTrendForecasting. pdf. Erişim Tarihi: 02.08.2023.
12. Dey, S., Kumar, Y., Saha, S., & Basak, S. (2016). Forecasting to Classification: Predicting the direction of stock market price using Xtreme Gradient Boosting. PESIT South Campus, 1-10. 10.13140/RG.2.2.15294.48968 Dixit, G., Roy, D., & Uppal, N. (2013). Predicting India volatility index: An application of artificial neural network. International Journal of Computer Applications, 70(4). Doi: 10.5120/11950-7768
13. Dorogush, A. V., Ershov, V., & Gulin, A. (2018). CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363.
14. Hann, T. H., & Steurer, E. (1996). Much ado about nothing? Exchange rate forecasting: Neural networks vs. linear models using monthly and weekly data. Neurocomputing, 10(4), 323-339. https://doi.org/10.1016/0925-2312(95)00137-9
15. Huang, W., Nakamori, Y., & Wang, S. Y. (2005). Forecasting stock market movement direction with support vector machine. Computers & operations research, 32(10), 2513-2522.
16. Hu, H., Tang, L., Zhang, S., & Wang, H. (2018). Predicting the direction of stock markets using optimized neural networks with Google Trends. Neurocomputing, 285, 188-195.
17. Hsu, M. W., Lessmann, S., Sung, M. C., Ma, T., & Johnson, J. E. (2016). Bridging the Divide In Financial Market Forecasting: Machine Learners & Financial Economists. Expert Systems With Applications, 61, 215-234.
18. Jhaveri, K., Shah, D., Bhanushali, S., & Johri, E. (2016, April). Financial market prediction using hybridized neural approach. In 2016 International Conference on Computation of Power, Energy Information and Commuincation (ICCPEIC) (pp. 009-014). IEEE.
19. Jiao, Y., & Jakubowicz, J. (2017, December). Predicting stock movement direction with machine learning: An extensive study on S&P 500 stocks. In 2017 IEEE International Conference on Big Data (Big Data) (pp. 4705-4713). IEEE.
20. Kara, Y., Boyacioglu, M. A., & 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.
21. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T. Y. (2017,December). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30, LongBeach,CA,USA.
22. Khaidem, L., Saha, S., & Dey, S. R. (2016). Predicting the direction of stock market prices using random forest. arXiv preprint arXiv:1605.00003.
23. Kumar, D., Meghwani, S. S., & Thakur, M. (2016). Proximal Support Vector Machine Based Hybrid Prediction Models for Trend Forecasting In Financial Markets. Journal of Computational Science, 17, 1-13.
24. Kumar, M., & Thenmozhi, M. (2006, January). Forecasting stock index movement: A comparison of support vector machines and random forest. In Indian institute of capital markets 9th capital markets conference paper. http://dx.doi.org/10.2139/ssrn.876544
25. Leung, M. T., Daouk, H., & Chen, A. S. (2000). Forecasting stock indices: a comparison of classification and level estimation models. International Journal of forecasting, 16(2), 173-190.
26. Mehta, S., Rana, P., Singh, S., Sharma, A., & Agarwal, P. (2019, August). Ensemble learning approach for enhanced stock prediction. In 2019 Twelfth International Conference on Contemporary Computing (IC3) (pp. 1-5). IEEE.
27. Nava, N., Di Matteo, T., & Aste, T. (2016). Time-dependent scaling patterns in high frequency financial data. The European Physical Journal Special Topics, 225, 1997-2016.
28. Ünlü, M. (2023). Borsa endeksi ve makroekonomik değişkenler arasındaki zamanla değişen nedensellik ilişkisi: Bist 100 endeksi üzerinden ampirik kanıtlar. Pamukkale Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, (60), 243-256.
29. Pabuçcu, H. (2019). Borsa endeksi hareketlerinin tahmini: trend belirleyici veri. Selçuk Üniversitesi Sosyal Bilimler Meslek Yüksekokulu Dergisi, 22(1), 246-256.
30. Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert systems with applications, 42(1), 259-268.
31. Prasad, A., & Bakhshi, P. (2022). Forecasting the Direction of Daily Changes in the India VIX Index Using Machine Learning. Journal of Risk and Financial Management, 15(12), 552.
32. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018, December 3-8). CatBoost: unbiased boosting with categorical features. Advances in neural information processing systems, 31, Montréal, Canada.
33. Quinlan, J. R. (1986). Induction of decision trees. Machine learning, 1, 81-106.
34. Quinlan, J. R. (1993). C4. 5: Programs for machine learning (Vol. 1). Morgan kaufmann.
35. Saad, E. W., Prokhorov, D. V., & Wunsch, D. C. (1998). Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks. IEEE Transactions on neural networks, 9(6), 1456-1470.
36. Shynkevich, Y., McGinnity, T. M., Coleman, S. A., Belatreche, A., & Li, Y. (2017). Forecasting price movements using technical indicators: Investigating the impact of varying input window length. Neurocomputing, 264, 71-88.
37. Thakkar, A., & Chaudhari, K. (2021). Fusion in stock market prediction: a decade survey on the necessity, recent developments, and potential future directions. Information Fusion, 65, 95-107.
38. Tsaih, R., Hsu, Y., & Lai, C. C. (1998). Forecasting S&P 500 stock index futures with a hybrid AI system. Decision support systems, 23(2), 161-174.
39. Weng, B., Ahmed, M. A., & Megahed, F. M. (2017). Stock market one-day ahead movement prediction using disparate data sources. Expert Systems with Applications, 79, 153-163.
40. Xia, Y., Liu, C., Li, Y., & Liu, N. (2017). A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring. Expert systems with applications, 78, 225-241.
41. Yang, J., Rao, R., Hong, P., & Ding, P. (2016, December,16-19). Ensemble model for stock price movement trend prediction on different investing periods. 12th International Conference on Computational Intelligence and Security (CIS), Wuxi, China
42. Yu, L., Chen, H., Wang, S., & Lai, K. K. (2009, February,19). Evolving least squares support vector machines for stock market trend mining. IEEE transactions on evolutionary computation, 13(1), 87-102.
43. Yu, L., Wang, S., & Lai, K. K. (2005, December). Mining stock market tendency using GA-based support vector machines. International workshop on Internet and network economics, Springer Berlin Heidelberg.