Makine öğrenmesi yöntemleri ile hisse senedi fiyat tahmini: kâğıt firması örneği

Öz

Bir finansal formül kullanarak hisse senedi fiyatlarını tahmin etmek zordur. Hisse senetleri fiyatları, siyasi gelişmeler, küresel ekonomi, beklenmedik olaylar, piyasa anormallikleri ve ilgili şirketlerin özellikleri gibi çok sayıda faktörden etkilenir. Hisse senedi fiyatlarına ilişkin daha doğru tahminler yapmak için bilgisayar biliminin gelişmesiyle birlikte birçok bilgisayar bilimi yöntemi kullanılmaktadır. Bu çalışmada, Kartonsan şirketinin hisse senedi fiyatını tahmin etmek için doğrusal regresyon (LR) algoritmaları, rastgele orman (RF), gradyan güçlendirme makinesi (GBM) ve yapay sinir ağları (YSA) gibi makine öğrenmesi teknikleri kullanılmıştır. Daha sonra kullanılan algoritmaların sonuçları karşılaştırılmıştır. Hisse senedi fiyatı tahmini için ilk olarak BIST (Borsa İstanbul)’te işlem gören Kartonsan firmasının 2011-2022 yılları arasındaki üçer aylık finansal çizelgeler kullanılarak firmaya ait finansal oran hesaplanmıştır ve bu oranlar girdi olarak kullanılmıştır. Çıktı olarak kullanılan firmanın hisse senedi fiyatlarının ise üçer aylık ortalamaları alınmıştır. GBM ve RF algoritmaları başarılı tahmin sonuçlarına sahip olmasına rağmen GBM algoritması en başarılı sonucu vermiştir. RF algoritmasının ise LR ve YSA’ya göre daha iyi performans gösterdiği bulunmuştur. YSA’nın hisse senedi fiyat tahmininde en kötü performansa sahip teknik olduğu belirlenmiştir.

Anahtar Kelimeler

• Hisse senedi fiyatı
• gradyan güçlendirme
• rastgele orman
• doğrusal regresyon
• yapay sinir ağları
• tahmin

Stock price prediction with machine learning methods: the case of paper company

Öz

It is difficult to predict stock prices using a financial formula. Stock prices are affected by numerous factors, including political developments, the global economy, unexpected events, market anomalies and the characteristics of the companies involved. With the development of computer science, many computer science methods are being used to make more accurate predictions of stock prices. In this study, machine learning techniques such as linear regression (LR) algorithms, random forest (RF), gradient boosting machine (GBM) and artificial neural Networks (ANN) were used to predict the stock price of Kartonsan company. Then, the results of the algorithms used were compared. For stock price prediction, firstly, the company's financial ratio was calculated using the quarterly financial statements of Kartonsan company, which is traded on BIST (Borsa Istanbul), between 2011 and 2022, and these ratios were used as input. Quarterly averages of the company's stock prices used as output were taken. Although GBM and RF algorithms have successful prediction results, the GBM algorithm gave the most successful results. It has been found that the RF algorithm performs better than LR and ANN. ANN has been identified as the technique with the worst performance in stock price prediction.

Anahtar Kelimeler

• Stock price
• Gradient boosting
• Random forest
• Linear regression
• Artificial neural network
• Prediction

Kaynakça

1. Abd Elminaam DS, El Tanany A, Abdul Salam M, Abd El Fattah M (2022) Closing price prediction of stock market using machine learning models. 2nd International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), Cairo, Egypt, pp. 251-255.
2. Acharya S, Pustokhina IV, Pustokhin DA, Geetha BT, Joshi GP, Nebhen J, Seo C (2021) An improved gradient boosting tree algorithm for financial risk management. Knowledge Management Research & Practice, 1-12.
3. Ahmad M, Reynolds J, Rezgui Y (2018) Predictive modelling for solar thermal energy systems: a comparison of support vector regression, random forest, extra trees and regression trees. J Clean Prod, 203: 810–821.
4. Akşehir ZD, Kılıç E (2019) Makine öğrenmesi teknikleri ile banka hisse senetlerinin fiyat tahmini. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, 12(2): 30-39.
5. Akyol Özcan K (2023) Borsa endeksi yönünün makine öğrenmesi yöntemleri ile tahmini: BIST 100 örneği. Gümüşhane Üniversitesi Sosyal Bilimler Dergisi, 14(3): 1001-1018.
6. Ali M, Khan DM, Aamir M, Ali A (2021) Predicting the direction movement of financial time series using artificial neural network and support vector machine. Complexity, Special Issue, 1-13.
7. Anonim (2022) Kağıt Sektör Raporu 2021. T.C. Sanayi ve Teknoloji Bakanlığı Sanayi Genel Müdürlüğü.
8. Arslankaya S, Toprak Ş (2021) Makine öğrenmesi ve derin öğrenme algoritmalarını kullanarak hisse senedi fiyat tahmini. Uluslararası Mühendislik Araştırma ve Geliştirme Dergisi, 13(1): 178-192.

9. Attrapadung N, Hamada K, Ikarashi D, Kikuchi R, Matsuda T, Mishina I, Morita H, Schuldt JCN (2022) Adam in private: secure and fast training of deep neural networks with adaptive moment estimation. Proceedings on Privacy Enhancing Technologies, 4: 746-767.
10. Bhardwaj N, Akil Ansari MD (2019) Prediction of stock market using machine learning algorithms. International Research Journal of Engineering and Technology, 6(5): 5994-6005.
11. Biau G, Scornet EA (2016) Random forest guided tour. Test, 25: 197–227. Botchkarev A (2018) Performance metrics (error measures) in machine learning regression, forecasting and prognostics: properties and typology.
12. Cavalcante RC, Brasileiro RC, Souza VLF, NobregaJP, Oliveira AI (2016) Computational intelligence and financial markets: a survey and future directions. Expert Systems with Applications, 55: 194-211.
13. Cao M (2021) Predicting the link between stock prices and indices with machine learning in R programming language. Journal of Mathematics, 2021: 1275637.
14. Ceylan T (2018) Perakende sektöründe makine öğrenmesine dayalı yaklaşımlar. Yıldız Teknik Üniversitesi Fen Bilimleri Enstitüsü Doktora Tezi, İstanbul.
15. Correa-Jullian C, Cardemil JM, Droguett EL, Behzad M (2020) Assessment of deep learning techniques for prognosis of solar thermal systems. Renewable Energy, 145: 2178-2191.
16. Devadoss AV, Ligori TAA (2013) Stock prediction using artificial neural networks. International Journal of Data Mining Techniques and Applications, 2: 283-291.
17. Dike HU, Zhou Y, Deveerasetty KK, Wu Q (2018) Unsupervised learning based on artificial neural network: a review. 2018 IEEE International Conference on Cyborg and Bionic Systems (CBS), Shenzhen, China, pp. 322-327.
18. Doğan S, Büyükkör Y (2022) Makine öğrenmesi ile finansal zaman serisi tahminleme. Ankara Hacı Bayram Veli Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 24(3): 1205-1230.
19. Ghani MU, Awais M, Muzammul M (2019) Stock market prediction using machine learning (ML) algorithms. Advances in Distributed Computing and Artificial Intelligence Journal, 8(4): 97-116.
20. Hartanto A, Kholik YN, Pristyanto Y (2023) Stock price time series data forecasting using the light gradient boosting machine (LightGBM) model. International Journal on Informatics Visualization, 7(4): 2270-2279.
21. He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, pp. 1026-1034.
22. Hu Q, Qin S, Zhang S (2022) Comparison of stock price prediction based on different machine learning approaches. Proceedings of the 2022 International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2022), Wuhan, Hubei province, China, pp. 215-231.
23. Hu J, Szymczak S (2023) A review on longitudinal data analysis with random forest. Briefings in Bioinformatics, 24(2): 1-11.
24. Idowu PA, Osakwe C, Kayode AA, Adagunodo ER (2012) Prediction of stock market in Nigeria using artificial neural network. I.J. Intelligent Systems and Applications, 11: 68-74.
25. Kaynar T, Yiğit ÖE (2021) Öznitelik mühendisliği ile makine öğrenmesi yöntemleri kullanılarak BIST 100 endeksi değişiminin tahminine yönelik bir yaklaşım. Journal of Yaşar University 16(64): 1741-1762.
26. Kesharwani H, Mallick T, Nakarmi A, Raj G (2023) Evaluation of stock prices prediction using recent machine learning algorithms. In B. Unhelkar, H. M. Pandey, A. P. Agrawal, A. Choudhary (Eds.), Advances and Applications of Artificial Intelligence & Machine Learning. Lecture Notes in Electrical Engineering, Singapore, Springer, pp. 557-566.
27. Kocaoğlu D, Turgut K, Konyar MZ (2022) Sector-based stock price prediction with machine learning models. Sakarya University Journal of Computer and Information Sciences, 5(3): 415-426.
28. Konstantinov AV, Utkin LV (2021) Interpretable machine learning with an ensemble of gradient boosting machines. Knowledge-Based Systems, 222: 106993.
29. Koç Ustalı N, Tosun N, Tosun Ö (2021) Makine öğrenmesi teknikleri ile hisse senedi fiyat tahmini. Eskişehir Osmangazi Üniversitesi İİBF Dergisi, 16(1): 1-16.
30. Leippold M, Wang Q, Zhou W (2022) Machine learning in the Chinese stock market. Journal of Financial Economics, 145: 64-82.
31. Lu H, Mazumder R (2020) Randomized gradient boosting machine. SIAM Journal on Optimization, 30(4): 2780-2808.
32. Manojlović T, Štajduhar I (2015) Predicting stock market trends using random forests: a sample of the Zagreb stock exchange. 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Croatia, pp. 1189-1193.
33. Moghaddam AH, Moghaddam MH, Esfandyari M (2016) Stock market index prediction using artificial neural network. Journal of Economics, Finance and Administrative Science, 21: 89-93.
34. Nakagawa K, Yoshida K (2022) Time-series gradient boosting tree for stock price prediction. Data, Mining, Modelling and Management, 14(2): 110-125.
35. Özşahin Ş (2012) The use of an artificial neural network for modelling the moisture absorption and thickness swelling of oriented strand board. BioResources, 7(1): 1053-1067.
36. Öztürkmen M, Eren E (2020) BIST 100 endeksi için yükseliş-düşüş tahmini için bir yapay öğrenme modeli. Efil Journal, 3(12): 42-52.
37. Patel R, Choudhary V, Saxena D, Singh AK (2021) Review of stock prediction using machine learning techniques. Proceedings of the Fifth International Conference on Trends in Electronics and Informatics (ICOEI),Tirunelveli, TamilNadu, India, pp. 840-846.
38. Qi M, Zhang G (2001) An investigationofmodel selection criteria forneural network time series forecasting. European J. Oper. Res., 13 (3): 666–680.
39. Ravikumar S, Saraf P (2020) Prediction of stock prices using machine learning (regression, classification) algorithms. 2020 International Conference for Emerging Technology (INCET), Belgaum, India, pp. 1-5.
40. Reddy PV, Kumar SM (2022) A method for determining the accuracy of stock prices using gradient boosting and the support vector machines algorithm. Proceedings of the Third International Conference on Smart Electronics and Communication (ICOS) Trichy, India, pp. 1596-1599.
41. Reddy PV, Kumar SM (2023) A novel approach to improve accuracy in stock price prediction using gradient boosting machines algorithm compared with random forest algorithm. AIP Conference Proceedings, 2822(1): 1-8.
42. Roy SS, Chopra R, Lee KC, Spampinato C, Mohammadi-ivatlood B (2020) Random forest, gradient boosted machines and deep neural network for stock price forecasting: a comparative analysis on South Korean companies. International Journal of Ad Hoc and Ubiquitous Computing, 33(1): 62-71.
43. Rubio A, Bermudez JD, Vercher E (2016) Forecasting portfolio returns using weighted fuzzy time series methods. International Journal of Approximate Reasoning, 75: 1-12.
44. Sakhare NN, Imambi SS (2019) Performance analysis of regression based machine learning techniques for prediction of stock market movement. International Journal of Recent Technology and Engineering, 7(6S): 655-662.
45. Sharma A, Bhuriya D, Singh U (2017) Survey of stock market prediction using machine learning approach. International Conference on Electronics, Communication and Aerospace Technology Coimbatore, India: 506-509.
46. Shrivastav LK (2022) An ensemble of random forest gradient boosting machine and deep learning methods for stock price prediction. Journal of Information Technology Research, 15(1): 1-19.
47. Singh G (2022) Machine learning models in stock market prediction. International Journal of Innovative Technology and Exploring Engineering, 11(3): 18-28.
48. Siswoyo B (2021) Ensemble learning gradient boosting in improving classification and prediction in machine learning. Turkish Journal of Computer and Mathematics Education, 12(8): 1997-2002.
49. Sorayaei A, Atf Z, Gholami M (2016) Prediction stock price using artificial neural network (case study: chemical industry fims accepted in Tehran stock exchange). Bulletin de la Societe Royale des Sciences, 85: 991-998.
50. Srivastava R, Kumar S, Kumar B (2023) Classification model of machine learning for medical data analysis. In T. Goswami, G. R. Sinha (Eds.), Statistical Modeling in Machine Learning: Concepts and Applications, Cambridge, Massachusetts, ABD Academic Press.
51. Su X, Yan X, Tsai CL (2012) Linear regression. Wiley Interdisciplinary Reviews: Computational Statistics, 4(3): 275-294
52. Tekin S, Çanakoğlu E (2018) Borsa İstanbul hisse senedi getirilerinin makine öğrenmesi yöntemleriyle tahmini. 26th Signal Processing and Communications Applications Conference, İzmir, Türkiye, pp. 1-4.
53. Toprak Ş, Çağıl G, Kökçam AH (2023) Stock closing price prediction with machine learning algorithms: PETKM stock example in BIST. Düzce University Journal of Science & Technology, 11: 958-976.
54. Touzani S, Granderson J, Fernandes S (2018) Gradient boosting machine for modeling the energy consumption of commercial buildings. Energy and Buildings, 158: 1533-1543.
55. Umoh UA. Eyoh IJ, Murugesan VS, Nyoho EE (2022) Fuzzy-machine learning models for the prediction of fire outbreaks: a comparative analysis. In R. Pandey, S. K. Khatri, N. K. Singh, P. Verma (Eds.), Artificial Intelligence and Machine Learning for EDGE Computing, Cambridge, Massachusetts, ABD: Academic Press, pp. 207-233.
56. URL-1. (2023). https://tr.investing.com/equities/kartonsan. Erişim tarihi: 15.10.2023
57. URL-2. (2023). https://www.kap.org.tr/tr/sirket-bilgileri/ozet/997-kartonsan-karton-sanayi-ve-ticaret-a-s. Erişim tarihi: 15.10.2023
58. URL-3. (2024). https://www.kartonsan.com.tr/tr/#. Erişim tarihi: 20.01.2024
59. Verma A, Soni R (2022) Predicting stock market movement employing data filtration and gradient boost algorithm. In A. Abraham, P. Siarry, V. Piuri, N. Gandhi, G. Casalino, O. Castillo, P. Hung (Eds.), Hybrid Intelligent Systems. HIS 2021. Lecture Notes in Networks and Systems Cham, Springer, pp. 215-222.
60. Vijh M, Chandola D, Tikkiwal VA, Kumar A (2020) Stock closing price prediction using machine learning techniques. Procedia Computer Science, 167: 599–606.
61. Wang J, Gao RX (2022) Innovative smart scheduling and predictive maintenance techniques. In D. Mourtzis (Ed.), Design and Operation of Production Networks for Mass Personalization in the Era of Cloud Technology ABD: Elsevier, pp.181-207.
62. Xu X (2022) Research on the stock price forecasting of netflix based on linear regression, decision tree, and gradient boosting models. Proceedings of the 2022 2nd International Conference on Business Administration and Data Science (BADS 2022) Kashgar, Xinjiang, China, pp. 1232-1242.
63. Yıldırım İ, Özşahin Ş, Akyüz KC (2011) Prediction of the financial return of the paper sector with artificial neural networks. BioResources, 6(4): 4076-4091.
64. Zahedi J, Rounaghi MM (2015) Application of artificial neural network models and principal componenet analysis method in predicting stock prices on Tehran Stock Exchange. Physcia A: Statistical Mechanics and Its Applications, 438: 177-187.