Hisse Senedi Fiyat Tahmininde Makine Öğrenimi Algoritmalarının Karşılaştırmalı Analizi

Abstract

Hisse senedi bir şirketin anaparasının bir parçasıdır. Bir şirketin hisselerini satın alan kişi, bu şirketin kar veya zararına ortak olur. Hisse senetlerinin işlem gördüğü borsalarda büyük hacimli işlemler yapılmaktadır. Hisse senedi fiyatları birçok değişkenden etkilendiğinden tahmin edilmesi zordur ancak tahmin edilebildiğinde büyük faydalar sağlanır. Hisse senedi fiyatlarının tahmini, makine öğrenmesi algoritmalarını kullanan günümüz bilgisayarları ile mümkün olmaktadır. Makine öğrenimi, hisse senedi fiyat tahmininde temel ve teknik analize göre daha başarılı sonuçlar sağlamaktadır. Çalışmamızda 2016-2020 yılları arasında BIST 100'de işlem gören en yüksek piyasa değerine sahip 5 hisse senedinin yaklaşık 5 yıllık verileri toplanarak günlük kapanış fiyatı tahminleri yapılmıştır. Çoklu doğrusal regresyon, bayesian regresyon, rastgele orman, karar ağaçları, destek vektör makineleri, yapay sinir ağları maksimum 22 özelliği dahil edecek şekilde uygulanmış ve sonuçlar karşılaştırılmıştır. En başarılı sonuç yapay sinir ağları algoritmasında elde edilmiştir. En yüksek başarıyı elde etmek için veri ön işleme, normalleştirme, çapraz doğrulama, parametre optimizasyonu ve özellik seçimi uygulanmıştır. Bu yöntemlerin bir arada kullanılmasının başarıyı arttırdığı gözlemlenmiştir.

Keywords

• Makine Öğrenmesi
• Algoritmalar
• Hisse Senedi
• Regresyon
• Gözetimli Öğrenme

Comparative Analysis of Machine Learning Algorithms in Stock Price Prediction

Abstract

Stock is part of a company's principal. A person who buys stock of a company shares the profit or loss of this company. Large volume transactions are made on stock exchanges where stocks are traded. Stock prices are difficult to predict because they are affected by many variables, but when they can be predicted, great benefits are provided. Prediction of stock prices is possible with today's computers using machine learning algorithms. Machine learning provides more successful results than fundamental and technical analysis in stock price prediction. In our study, daily closing price predictions were made by collecting approximately 5-years data of the top 5 stocks with the highest market value traded in BIST 100 between 2016 and 2020. Multiple linear regression, Bayesian regression, random forest, decision trees, support vector machines, artificial neural networks algorithms were applied to include maximum 22 features and the results were compared. The most successful result was obtained in the artificial neural networks algorithm. To achieve the highest success, data pre-processing, normalization, cross-validation, parameter optimization and feature selection were applied. It has been observed that using these methods together increases the success.

Keywords

• Machine Learning
• Algorithms
• Stock
• Regression
• Supervised Learning

References

1. Summers, D. (2007) Longman Business English Dictionary, Pearson Longman, London, 594 p.
2. URL-1: https://dataconomy.com/2023/01/11/stock-prediction-machine-learning. [Access date: 20.04.2023]
3. URL-2: https://builtin.com/machine-learning/machine-learning-stock-prediction. [Access date: 20.04.2023]
4. Hürer, E. (1995) Hisse Senedi Fiyatını Etkileyen Faktörler ve İMKB Üzerine Bir Uygulama, İstanbul University, İstanbul, 208 s.(Master Thesis)
5. Ghani, M., Awais, M., Muzammul (2019), Stock Market Prediction Using Machine Learning(ML) Algorithms, Advances in Distributed Computing and Artificial Intelligence Journal, 4, pp. 97-116.
6. Sarode, S., Tolani, H., Kak, P., Lifna, C. (2019) Stock Price Prediction Using Machine Learning Techniques, International Conference on Intelligent Sustainable Systems (ICISS), Palladam, India.
7. Usmani, M., Adil, S., Raza, K., Ali, S. (2016) Stock Price Prediction Using Machine Learning Techniques. 3rd International Conference On Computer And Information Sciences (ICCOINS), Kuala Lumpur, Malaysia.
8. Tipirisetty, A. (2018) Stock Price Prediction using Deep Learning. San Jose State University, Department of Computer Science, California, 54s. (Master Thesis) Singh, S. Stock Prediction using Machine Learning, California State University, Computer Science, California, 2021, 16s. (Master Thesis).

9. Guo, Y. Stock Price Prediction Using Machine Learning, Sodertorn University, School of Social ScienceMaster, Economics, Stockolm, 2022, 34. (Master Thesis).
10. Molnar C. (2019) Interpretable Machine Learning, Lulu.com, 314 p.
11. Bi, Q., Goodman, K. E., Kaminsky, J., Lessler, J.(2019) What is machine learning? A primer for the epidemiologist, American journal of epidemiology, 188(12), 2222-2239.
12. URL-3 //www.isyatirim.com.tr/tr-tr/analiz/hisse/Sayfalar/Temel-Degerler-Ve-Oranlar. [Access date: 12.12.2022]
13. Aslan, B. (2020), Derin Öğrenme ile Borsa Verileri Üzerinde Tahminleme Yapılması, Ege Üniversitesi, İzmir, 61. (Master Thesis)
14. URL-4: https://borsaistanbul.com/tr/sayfa/506/pazarlar [Access date: 18.12.2022]
15. URL-5: https://www.alnusyatirim.com/bist-100 [Access date: 18.12.2022]
16. Karagöz, S. (2020), Payların Kapanış Fiyatlarının Makine Öğrenmesi Yöntemleri ile Tahmin Edilmesi,, İstanbul , 118. (master Thesis).
17. URL-6: https://bigpara.hurriyet.com.tr/ [Access date: 21.11.2022]
18. URL-7: https://en.wikipedia.org/wiki/S%26P_500 [Access date: 22.12.2022]
19. URL-8: https://en.wikipedia.org/wiki/EURO_STOXX [Access date: 22.12.2022]
20. URL-9 https://www.tcmb.gov.tr/ [Access date: 23.12.2022]
21. Kotsiantis, S.B., Kanellopoulos, D., Pintelas P.E.(2006), Data Preprocessing for Supervised Leaning. International Journal of Computer Science Volume 1, pp. 111-117
22. Alexandropoulos, S.N., Kotsiantis S.B., Vrahatis M.N. (2019), Data Preprocessing in Predictive Data Mining, Cambridge University Press 34 E1.
23. King, R., Orhobor, O., Taylor, C (2019) Cross-Validation is Safe to Use, Nature Machine Intelligence. 2021, 3, pp. 276-276.
24. Daniel, B. (2021) Cross-Validation, Data Science Laboratory, 2, pp. 542-545.
25. Chandrashekar, G., Sahin, F., A Survey on Feature Selection Methods. Computers & Electrical Engineering, 2014, 40, pp. 16-28.
26. Jović, A. and Brkić, K., Bogunović, N. A Review of Feature Selection Methods with Applications. 38th International Convention on Information and Communication Technology, 2015, Croatia.
27. Zhang, F., O’Donnel, L. Support Vector Regression, Machine Learning Methods and Applications to Brain Disorders. 2020, 7, pp. 123-140
28. Raju, G., Lakshmi, K., Jain, V., Kalidindi, A., Padma V., Study the Influence of Normalization/Transformation process on the Accuracy of Supervised Classification. Third International Conference on Smart Systems and Inventive Technology (ICSSIT), 2020, India.
29. Skinea, S., Data Science Design Manual, New York, USA, 2017, 453 s.
30. Liu, Y., Wang, Y., Zhang, J. New Machine Learning Algorithm: Random Forest. International Conference on Information Computing and Applications, 2012, pp 246-252)
31. URL-10 https://towardsdatascience.com/introduction-to-bayesian-linear-regression [Access date: 20.04.2023]
32. Bonaccorso, G. Machine Learning Algorithms., Packt Publishing, Birmingham, UK, 2017, 337s.
33. Ferreira, P., Le. D., Zincir-Heywood N., Exploring Feature Normalization and Temporal Information for Machine Learning Based Insider Threat Detection. 15th International Conference on Network and Service Management (CNSM), 21-25 October, 2019, Halifax, NS, Canada.
34. Robbach P. Neural Networks vs. Random Forests – Does it always have to be Deep Learning? Computer Science, 2018.