Application of Optimization Algorithms for Risk Minimization in a Portfolio of Automated Trading Systems

• Daniel Fernandes Campos UEFS
• Carlos Alberto Rodrigues UEFS
• Angelo C. Loula UEFS

DOI: https://doi.org/10.5753/bwaif.2022.223149

Abstract

The use of ATS (Automated Trading System) portfolios has become increasingly common in equity markets but this combination is accompanied by high volatility. To alleviate this situation, this work presents a study involving five optimization methods applied to an ATS portfolio operating in the Forex market to increase profits and reduce risk (drawdown), through the definition of optimal capital weights to be applied in each ATS. Technical analysis indicators were used as objective functions. A correlation filter and the Monte Carlo method for risk adjustment are also presented. In most cases, the optimizations based on Sharpe-Ratio and K-Ratio indicators obtained better results than the portfolio of equal weights and the correlation filter contributed to a decrease in risk but also with a decrease in profits.

Keywords: Automated Trading System, Computational finance, Algorithmic trading, Portfolio Optimization

References

Aldridge, I. (2013). High-frequency trading: a practical guide to algorithmic strategies and trading systems. John Wiley & Sons.

Bigiotti, A. and Navarra, A. (2019). Optimizing automated trading systems. In Antipova, T. and Rocha, A., editors, Digital Science, pages 254–261, Cham. Springer International Publishing.

Borch, C. and Min, B. H. (2022). Machine learning and social action in markets: From firstto second-generation automated trading. Economy and Society, 0(0):1–25.

Cavalcante, R. C., Brasileiro, R. C., Souza, V. L., Nobrega, J. P., and Oliveira, A. L. (2016). Computational intelligence and financial markets: A survey and future directions. Expert Systems with Applications, 55:194–211.

Contreras, I., Hidalgo, J. I., and Nunez-Letamendia, L. (2017). A hybrid automated trading system based on multi-objective grammatical evolution. Journal of Intelligent & Fuzzy Systems, 32(3):2461–2475.

Dickman, B. and Gilman, M. (1989). Monte carlo optimization. Journal of optimization theory and applications, 60(1):149–157.

Freitas, F. D., Freitas, C. D., and De Souza, A. F. (2013). System architecture for online optimization of automated trading strategies. In Proceedings of the 6th Workshop on High Performance Computational Finance, WHPCF ’13, New York, NY, USA. Association for Computing Machinery.

Guedes, A., Rodrigues, C., and Loula, A. (2021). Otimização evolutiva lexicográfica de um portfólio de estratégias automatizadas no mercado futuro brasileiro. In Anais do XVIII Encontro Nacional de Inteligência Artificial e Computacional, pages 458–469, Porto Alegre, RS, Brasil. SBC.

Hilpisch, Y. (2020). Python for Algorithmic Trading From Idea to Cloud Deployment. O’Reilly Media.

Huang, B., Huan, Y., Xu, L. D., Zheng, L., and Zou, Z. (2019). Automated trading systems statistical and machine learning methods and hardware implementation: a survey. Enterprise Information Systems, 13(1):132–144.

Katz, J. O. and McCormick, D. L. (2000). The encyclopedia of trading strategies. McGraw-Hill New York.

Kraft, D. (1988). A software package for sequential quadratic programming. Technical Report DFVLR-FB 88-28, DLR German Aerospace Center – Institute for Flight Mechanics, Koln, Germany.

Kroese, D. P., Brereton, T. J., Taimre, T., and Botev, Z. I. (2014). Why the monte carlo method is so important today. Wiley Interdisciplinary Reviews: Computational Statistics, 6.

Leshik, E. A. and Cralle, J. (2011). An introduction to algorithmic trading. John Wiley & Sons Ltd.

Macedo, L. L., Godinho, P., and Alves, M. J. (2017). Mean-semivariance portfolio optimization with multiobjective evolutionary algorithms and technical analysis rules. Expert Systems With Applications, 79(C):33–43.

Maier-Paape, S. (2018). Risk averse fractional trading using the current drawdown. Journal of Risk, 20(5):117–141.

Nunes, L. (2007). In Sahni, S., editor, Fundamentals of Natural Computing. Chapman & Hall CRC Computer and Information Science.

Pardo, R. (2011). The evaluation and optimization of trading strategies. John Wiley & Sons.

Parikh, V. and Shah, P. (2015). Stock prediction and automated trading system. International Journal of Computer Science & Communication, 6:104–111.

Pauna, C. (2018). Automated trading software-design and integration in business intelligence systems. Database Systems Journal, pages 22–28.

Queiroz, I. and Rodrigues, C. (2019). Comparação de métodos de position size nos mercados futuros do brasil. Revista da FAE, 22:67–82.

Raudys, A. and Pabarskaite, Z. (2012). Discrete portfolio optimisation for large scale systematic trading applications. In 2012 5th International Conference on BioMedical Engineering and Informatics, pages 1566–1570.

Raudys, S. (2013). Portfolio of automated trading systems: Complexity and learning set size issues. IEEE transactions on neural networks and learning systems, 24(3):448–459.

Romero Moreno, C. S. (2011). La teoría moderna de portafolio: Un ensayo sobre sus formulaciones originales y sus repercusiones contemporáneas. Observatorio de Economía y Operaciones Numéricas ODEON, pages 105–118.

Vezeris, D., Kyrgos, T., Karkanis, I., and Bizergianidou, V. (2020). Automated trading systems’ evaluation using d-backtest ps method and wm ranking in financial markets. Investment Management and Financial Innovations, 17(2):198–215.