Finansal Piyasalarda Algoritmik Ticaret İçin Genetik Algoritma Temeli Yaklaşım

Year 2023, Volume: 7 Issue: 2, 164 - 169, 31.12.2023

Yunus Santur , Mustafa Ulaş , Murat Karabatak

https://doi.org/10.46460/ijiea.1176888

Abstract

Finansal piyasalarda önceden belirlenmiş koşullara göre anlık al sat işlemlerinin yapılmasını sağlayan yazılımlara algoritmik ticaret denilmektedir. Algoritmik işlem robotları geliştirilirken genellikle teknik analizde kullanılan göstergeler kullanılmaktadır. Robotun strateji seçimi için geçmiş veriler üzerinde Backtest adı verilen işlem gerçekleştirilmektedir. Backtest işleminin amacı gerçekleştirilen başarılı/başarısız ticaret sayısı, aracı kuruma ödenecek komisyon sonrası portföy kasa değeri, kar faktörü ve sharpe oranı gibi değerlerin elde edilerek yorumlanması işlemidir. Bu süreçte en büyük dezavantaj uygun stok, periyot, indikatör ve bunlara ait parametrelerin seçimidir. Backtest işlemini optimal olarak en iyileyen bu parametrelerin seçiminde çoğunlukla doğrusal programlama yaklaşımları kullanılmaktadır. Ancak kullanılacak stratejiye göre bu algoritmaların kodlanması lineer bir karmaşıklıktan, quadratic veya polynomial karmaşıklığa sahip olabilmektedir. Bu durum yatırımcılar ve algoritmik robot geliştiriciler için uzun test süreleri gerektirmektedir. Doğadan esinlenerek geliştirilen genetik algoritma tabanlı yaklaşımlar ise çok daha az iterasyon ile optimal çözüme yakınsayarak, daha az işlem gücü ve zaman gerektirmektedir. Bu çalışmada algoritmik ticarette optimal koşulların seçimi için genetik programlama tabanlı bir yaklaşım önerilmiştir. Deneysel çalışmalar bölümünde, geleneksel ve genetik algoritma tabanlı yaklaşımların karmaşıklık, benchmark ve Backtest sonuçları karşılaştırıldığında algoritmik ticaret işlemlerinde kullanılmasının avantajlara sahip olduğu görülmüştür.

Keywords

finansal tahmin, zaman serileri, algoritmik ticaret

Project Number

121E733

Genetic Algorithm Based Approach for Algorithmic Trading in Financial Markets

Abstract

Software that enables realtime buy and sell transactions in financial markets according to predetermined conditions is called algorithmic trading. When developing algorithmic trading robots, indicators used in technical analysis are generally used. For the strategy selection of the robot, a process called Backtest is performed on the historical time series. The purpose of the Backtest process is the process of obtaining and interpreting values such as the number of successful/unsuccessful trades, the portfolio cash value after the commission to be paid to the intermediary institution, the profit factor and the sharpe ratio. The biggest disadvantage in this process is the selection of the appropriate stock, period, indicator and their parameters. Linear programming approaches are mostly used in the selection of these parameters that optimize the Backtest process optimally. However, according to the strategy to be used, the coding of these algorithms can have a linear, quadratic or polynomial complexity. This requires more long testing times for investors and algorithmic robot developers. Genetic algorithm-based approaches inspired by nature, on the other hand, converge to the optimal solution with much less iteration and require less processing power and time. In this study, a genetic programming-based approach is proposed for the selection of optimal conditions in algorithmic trading. In the experimental studies section, it has been seen that the use of traditional and genetic algorithm-based approaches in algorithmic trading operations has advantages when comparing complexity.

Keywords

Algorithmic trading, genetic algorithm, optimization

Supporting Institution

TÜBİTAK

Project Number

121E733

Thanks

This work was supported by the Scientific and Technological Research Council of Turkey (TUBITAK, Grant No. 121E733).

References

• Christodoulaki, E., Kampouridis, M., & Kanellopoulos, P. (2022, May). Technical and sentiment analysis in financial forecasting with genetic programming. In 2022 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFER) (pp. 1-8). IEEE.
• Cheng, WK, Bea, KT, Leow, SMH, Chan, JYL, Hong, ZW, & Chen, YL (2022). A Review of Sentiment, Semantic and Event-Extraction-Based Approaches in Stock Forecasting. Mathematics, 10(14), 2437.
• Cheng, D., Yang, F., Xiang, S., & Liu, J. (2022). Financial time series forecasting with multi-modality graph neural network. Pattern Recognition, 121, 108218.
• Dai, C. (2022). A method of forecasting trade export volume based on back-propagation neural network. Neural Computing and Applications, 1-10.
• Mehtab, S., & Sen, J. (2022). Analysis and forecasting of financial time series using CNN and LSTM-based deep learning models. In Advances in Distributed Computing and Machine Learning (pp. 405-423). Springer, Singapore.
• Santur, Y. (2020). Deep learning based regression approach for algorithmic stock trading: A case study of the Bist30. Gumushane University Journal of Science, 10(4), 1195-1211.
• Klein, T. (2022). A note on GameStop, short squeezes, and autodidactic herding: An evolution in financial literacy?. Finance Research Letters, 46, 102229.
• Sianturi, MS, & Kim, SS (2022). Technical Analysis and Value Investment in the Indonesia Stock Market. Budapest International Research and Critics Institute (BIRCI-Journal): Humanities and Social Sciences, 5(2).
• Achyutha, PN, Chaudhury, S., Bose, SC, Kler, R., Surve, J., & Kaliyaperumal, K. (2022). User Classification and Stock Market-Based Recommendation Engine Based on Machine Learning and Twitter Analysis. Mathematical Problems in Engineering, 2022.
• Shindler, M., Goodrich, MT, Gila, O., & Dillencourt, M. (2022). Beyond big O: teaching experimental algorithms. Journal of Computing Sciences in Colleges, 37(10), 23-36.
• Gao, R., Du, L., Yuen, KF, & Suganthan, PN (2021). Walk-forward empirical wavelet random vector functional link for time series forecasting. Applied Soft Computing, 108, 107450.
• Mukherjee, A., Singh, AK, Mallick, PK, & Samanta, SR (2022). Portfolio Optimization for US-Based Equity Instruments Using Monte-Carlo Simulation. In Cognitive Informatics and Soft Computing (pp. 691-701). Springer, Singapore.
• Sang, B. (2021). Application of genetic algorithm and BP neural network in supply chain finance under information sharing. Journal of Computational and Applied Mathematics, 384, 113170.
• Chen, T. (2021). Evaluation method of development level of Science and technology finance in Heilongjiang Province based on genetic projection Pursuit model. In 2021 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS) (pp. 805-809). IEEE.
• Wen, C., Yang, J., Gan, L., & Pan, Y. (2021). Big data driven Internet of Things for credit evaluation and early warning in finance. Future Generation Computer Systems, 124, 295-307.
• Wang, Q., Wang, R., & Ziegel, J. (2022). E-backtesting. arXiv preprint arXiv:2209.00991.
• Bailey, DH, & de Prado, ML (2021). How “backtest overfitting” in finance leads to false discoveries. Significance, 18(6), 22-25.
• Öntürk, A., Ulaş, M., Karabatak, M., & Santur, Y. Python for Finance: Open Source Tools and Development of an Algorithmic Robot.
• Rodrigues, MJ (2022). Data Science for finance: automated investment recommendation with python (Doctoral dissertation).
• Olivares, KG, Garza, F., Luo, D., Challú, C., Mergenthaler, M., & Dubrawski, A. (2022). HierarchicalForecast: A Reference Framework for Hierarchical Forecasting in Python. arXiv preprint arXiv:2207.03517.