Derin Öğrenme Tabanlı Fiyat Tahmini ve Algoritmik Ticaret: BİST100 Endeksinde Bir Uygulama

Year 2024, , 1194 - 1215, 27.09.2024

Ahmet Akusta , Mehmet Nuri Salur

https://doi.org/10.25295/fsecon.1447129

Abstract

Bu araştırma, BİST100 endeksinde yer alan hisse senetlerinin alım satımı için derin öğrenme tabanlı metodolojilerin kullanılmasını ele almaktadır. Özellikle, son dönemdeki piyasa dalgalanmaları üzerine yoğunlaşılmıştır. Tahmine Dayalı İşlem Algoritması (TDİA) adı verilen, derin öğrenme esaslı bir işlem algoritması geliştirilmiş ve bu algoritmanın BİST100'de temsil edilen çeşitli sektörlerdeki hisse senedi hareketlerini tahmin etme ve işlem gerçekleştirme başarısı değerlendirilmiştir. Çalışma, Ağustos 2022'den Aralık 2023'e kadar olan ve toplam 270 işlem gününü kapsayan veriler üzerine kuruludur. Algoritmik ticaret, ticaretin yürütülmesinde sağladığı verimlilik, hız ve hassasiyet sayesinde modern finans dünyasında önemli bir yere sahiptir. Özellikle BİST100 gibi dinamik piyasalarda, algoritmik alım satımın önemi, geleneksel stratejilerin hızlı değişimlere ve karmaşıklıklara uyum sağlama konusundaki zorlukları nedeniyle daha da belirginleşmektedir. Bu çalışmada benimsenen metodoloji, geçmiş fiyat, hacim, hisse senedi endeksi ve döviz kuru verilerini kullanarak gelecekteki hisse senedi hareketlerini tahmin etmeye yönelik derin öğrenme modelinin geliştirilmesini ve uygulanmasını kapsamaktadır. Bu model, alım veya satım emirlerini gerçekleştirmek üzere tanımlanmış kurallar seti üzerinde çalışan bir Tahmine Dayalı İşlem Algoritması'nın temelini oluşturmaktadır. Araştırmanın temel bulguları, TDİA'nın seçilen hisse senetlerinde ortalama %15,87 kar ile kayda değer bir başarı elde ettiğini göstermektedir. Bu sonuçlar, algoritmik ticaretin potansiyelini ve derin öğrenme metodolojilerinin finansal piyasalarda kullanımının etkinliğini vurgulamaktadır.

Keywords

Algoritmik Ticaret, Fiyat Tahmini, Derin Öğrenme, Tahmine Dayalı İşlem Algoritması

Deep Learning Based Price Prediction and Algorithmic Trading on BIST100

Abstract

This research addresses using deep learning-based methodologies for trading stocks in the BIST100 index. In particular, the focus is on recent market fluctuations. A deep learning-based trading algorithm called Predictive Trading Algorithm (PTA) is developed, and its success in predicting stock movements in various sectors represented in the BIST100 is evaluated. The study is based on data from August 2022 to December 2023, covering 270 trading days. Algorithmic trading is essential in the modern financial world thanks to its efficiency, speed, and precision in trade execution. Especially in dynamic markets such as the BIST100, the importance of algorithmic trading becomes even more evident due to the difficulties of traditional strategies in adapting to rapid changes and complexities. The methodology adopted in this study involves developing and applying a deep learning model to predict future stock movements using historical price, volume, stock index, and exchange rate data. This model forms the basis of a Predictive Trading Algorithm based on a defined set of rules to execute buy or sell orders. The main findings of the research show that the PTRA achieves remarkable success with an average profit of 15.87% on the selected stocks. These results emphasize the potential of algorithmic trading and the effectiveness of using deep learning methodologies in financial markets.

Keywords

Algorithmic Trading, Price Prediction, Deep Learning, Predictive Trading Algorithm

References

• Adegboye, A., Kampouridis, M. & Otero, F. (2023). Algorithmic Trading with Directional Changes. Artificial Intelligence Review, 56(6), 5619-5644. https://doi.org/10.1007/S10462-022-10307-0/TABLES/14
• Aloud, M. E. & Alkhamees, N. (2021). Intelligent Algorithmic Trading Strategy Using Reinforcement Learning and Directional Change. IEEE Access, 9, 114659-114671. https://doi.org/10.1109/ACCESS.2021.3105259
• Boehmer, E., Fong, K. & Wu, J. J. (2015). Algorithmic Trading and Market Quality: International Evidence. Journal of Financial and Quantitative Analysis, 56(8), 2659-2688. https://doi.org/10.1017/S0022109020000782
• Cartea, Á., Jaimungal, S. & Kinzebulatov, D. (2016). Algorithmic Trading with Learning. International Journal of Theoretical and Applied Finance, 19(4). https://doi.org/10.1142/S021902491650028X
• Cartea, Á., Jaimungal, S. & Ricci, J. (2018). Algorithmic Trading, Stochastic Control, and Mutually Exciting Processes. SIAM Review, 60(3), 673-703. https://doi.org/10.1137/18M1176968
• Chaboud, A. P., Chiquoine, B., Hjalmarsson, E. & Vega, C. (2014). Rise of the Machines: Algorithmic Trading in the Foreign Exchange Market. The Journal of Finance, 69(5), 2045-2084. https://doi.org/10.1111/JOFI.12186
• Çankal, A. & Yakut, E. (2016). Portfolio Optimization Using of Methods Multi Objective Genetic Algorithm and Goal Programming: An Application in BIST-30. Business and Economics Research Journal, 7(2), 43-43. https://doi.org/10.20409/BERJ.2016217495
• Garcia, D. & Schweitzer, F. (2015). Social Signals and Algorithmic Trading of Bitcoin. Royal Society Open Science. https://doi.org/10.1098/rsos.150288
• Hansen, K. B. (2020). The Virtue of Simplicity: On Machine Learning Models in Algorithmic Trading. Big Data & Society. https://doi.org/10.1177/2053951720926558
• Hatch, B. C., Johnson, S. A., Wang, Q. E. & Zhang, J. (2021). Algorithmic Trading and Firm Value. Journal of Banking & Finance, 125, 106090. https://doi.org/10.1016/J.JBANKFIN.2021.106090
• Kalaycı, C. B., Ertenlıce, O., Akyer, H. & Aygören, H. (2017). Ortalama-Varyans Portföy Optimizasyonunda Genetik Algoritma Uygulamaları Üzerine Bir Literatür Araştırması. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 23(4), 470-476. https://gcris.pau.edu.tr/handle/11499/43710
• Kelejian, H. H. & Mukerji, P. (2016). Does High Frequency Algorithmic Trading Matter for Non-AT Investors?. Research in International Business and Finance, 37, 78-92. https://doi.org/10.1016/J.RIBAF.2015.10.014
• Koegelenberg, D. J. C. & van Vuuren, J. H. (2024). A Dynamic Price Jump Exit and Re-Entry Strategy for Intraday Trading Algorithms Based on Market Volatility. Expert Systems with Applications, 243, 122892. https://doi.org/10.1016/J.ESWA.2023.122892
• Li, Y., Zheng, W. & Zheng, Z. (2019). Deep Robust Reinforcement Learning for Practical Algorithmic Trading. IEEE Access, 7, 108014-108021. https://doi.org/10.1109/ACCESS.2019.2932789
• Liu, P., Zhang, Y., Bao, F., Yao, X. & Zhang, C. (2023). Multi-Type Data Fusion Framework Based on Deep Reinforcement Learning for Algorithmic Trading. Applied Intelligence, 53(2), 1683-1706. https://doi.org/10.1007/S10489-022-03321-W/TABLES/15
• Lu, B., Hao, S., Pinedo, M. & Xu, Y. (2021). Frontiers in Service Science: Fintech Operations-An Overview of Recent Developments and Future Research Directions. Service Science. https://doi.org/10.1287/serv.2021.0270
• MacKenzie, D. (2018). ‘Making’, ‘Taking’ and the Material Political Economy of Algorithmic Trading. Economy and Society, 47(4), 501-523. https://doi.org/10.1080/03085147.2018.1528076
• Massei, G. (2023). Algorithmic Trading: An Overview and Evaluation of Its Impact on Financial Markets. http://dspace.unive.it/handle/10579/23509
• Ponomarev, E. S., Oseledets, I. V., & Cichocki, A. S. (2019). Using Reinforcement Learning in the Algorithmic Trading Problem. Journal of Communications Technology and Electronics, 64(12), 1450-1457. https://doi.org/10.1134/S1064226919120131/FIGURES/7
• Pricope, T.-V. (2021). Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review. https://arxiv.org/abs/2106.00123v1
• Sazu, M. H. (2022). How Machine Learning Can Drive High Frequency Algorithmic Trading for Technology Stocks. International Journal of Data Science and Advanced Analytics, 4(4), 84-93. https://ijdsaa.com/index.php/welcome/article/view/97
• Shavandi, A., & Khedmati, M. (2022). A multi-agent deep reinforcement learning framework for algorithmic trading in financial markets. Expert Systems with Applications, 208, 118124. https://doi.org/10.1016/J.ESWA.2022.118124
• Stefano, V. D., & Taes, S. (2022). Algorithmic Management and Collective Bargaining. Transfer European Review of Labour and Research. https://doi.org/10.1177/10242589221141055
• Tao, R., Su, C. W., Xiao, Y., Dai, K. & Khalid, F. (2021). Robo Advisors, Algorithmic Trading and Investment Management: Wonders of Fourth Industrial Revolution in Financial Markets. Technological Forecasting and Social Change, 163, 120421. https://doi.org/10.1016/J.TECHFORE.2020.120421
• Théate, T. & Ernst, D. (2021). An Application of Deep Reinforcement Learning to Algorithmic Trading. Expert Systems with Applications, 173, 114632. https://doi.org/10.1016/J.ESWA.2021.114632
• Uğur, Ö., Aladağlı, E. E. & Tekin, Ö. (2018). Algoritmik Ticaret ve Finansal Araçlar için Gerçek Zamanlı Çalışan Bir Prototip. https://open.metu.edu.tr/handle/11511/61719
• Upson, J. & Van Ness, R. A. (2017). Multiple Markets, Algorithmic Trading, and Market Liquidity. Journal of Financial Markets, 32, 49-68. https://doi.org/10.1016/J.FINMAR.2016.05.004
• Vo, A. & Yost-Bremm, C. (2020). A High-Frequency Algorithmic Trading Strategy for Cryptocurrency. Journal of Computer Information Systems, 60(6), 555-568. https://doi.org/10.1080/08874417.2018.1552090
• Weller, B. M. (2018). Does Algorithmic Trading Reduce Information Acquisition?. The Review of Financial Studies, 31(6), 2184-2226. https://doi.org/10.1093/RFS/HHX137
• Yadav, Y. (2015). How Algorithmic Trading Undermines Efficiency in Capital Markets. Vanderbilt Law Review, 68(6), 1607-1671.
• Zhang, X., Zhang, Y., Wang, S., Yao, Y., Fang, B. & Yu, P. S. (2018). Improving Stock Market Prediction via Heterogeneous Information Fusion. Knowledge-Based Systems. https://doi.org/10.1016/j.knosys.2017.12.025
• Zulkifli, Z. S., Surip, M., Mohammad, H., Zamri, N., Mamat, M. & Idris, N. S. U. (2023). Algorithmic Trading System Based on Technical Indicators in Artificial Intelligence: A Review. AIP Conference Proceedings, 2484(1). https://doi.org/10.1063/5.0110055/2879570