Mathematics and Computational Sciences

A hybrid framework integrating mathematical genetic Algorithm and Multi-Criteria decision making for robust Rule-Based stock market strategy optimization

Document Type : Original Article

Authors

Karen Felicita Chinraj
Sahaya Sudha Anthonysamy

Department of Mathematics, Nirmala College for Women, Coimbatore, India.

https://doi.org/10.30511/mcs.2025.2075467.1556
Abstract
Financial markets exhibit nonlinear dynamics, regime shifts, and conflicting performance objectives, making traditional optimization methods insufficient for robust trading strategy design. This study proposes a hybrid framework integrating a Mathematical Genetic Algorithm (MGA) with a Multi-Criteria Decision-Making (MCDM) method for evolving interpretable, rule-based trading strategies. The MGA employs mathematically governed operators and integer-constrained parameter evolution, while the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method evaluates candidates across return, risk, drawdown, and volatility. Using NIFTY NEXT 50 data and walk-forward validation, the proposed framework achieves superior risk-adjusted performance compared to a buy-and-hold benchmark, yielding higher annualized returns (0.165), higher Sharpe ratio (1.32), and lower maximum drawdown (0.080). Sensitivity analysis confirms robustness to variations in the MGA penalty parameter λ and TOPSIS weights. Findings demonstrate that embedding MCDM within MGA improves interpretability, multi-objective balance, and out-of-sample stability, offering a practical pathway for intelligent trading system design.

Keywords

Mathematical genetic algorithm
Multi-Criteria decision making
Nifty next 50
Rule-Based trading
Walk-Forward validation

Subjects

[1] Adegboye. A, Kampouridis. A. (2022). On GA-optimized directional changes strategies, IEEE Conference Paper.
[2] Alaminos. D, Quesada. A, Salas. R. (2024). Hybrid genetic algorithms in agent-based artificial market simulation, Applied Soft Computing. 
[3] Alsanousi, A. T., Alqahtani, A. Y., Makki, A. A., Baghdadi, M. A. (2024). A hybrid MCDM approach using the BWM and the TOPSIS for a financial performance-based evaluation of Saudi stocks. Information, 15(5), 258. 
[4] Menoita, R., Silva, S. (2025). Evolving Financial Trading Strategies with Vectorial Genetic Programming. arXiv preprint arXiv:2504.05418.
[5] Chang, Y. H., Huang, C. W. (2024). Utilizing Genetic Algorithms in Conjunction with ANN-Based Stock Valuation Models to Enhance the Optimization of Stock Investment Decisions. AI, 5(3), 1011-1029. 
[6] Christodoulaki, E., Kampouridis, M., Kyropoulou, M. (2025). A novel strongly-typed Genetic Programming algorithm for combining sentiment and technical analysis for algorithmic trading. Knowledge-Based Systems, 311, 113054. 
[7] Rani, S., Dhanasekar, S. (2025). Type-2 Trapezoidal Pythagorean fuzzy number with novel entropy measure and aggregation operators extended to MCDM. Complex Intelligent Systems, 11(10), 1-45. 
[8] Oyewola, D. O., Dada, E. G., Ndunagu, J. N. (2022). A novel hybrid walk-forward ensemble optimization for time series cryptocurrency prediction. Heliyon, 8(11). 
[9] Narayanamoorthy, S., Ramya, L., Gunasekaran, A., Kalaiselvan, S., Kang, D. (2023). Selection of suitable biomass conservation process techniques: a versatile approach to normal wiggly interval-valued hesitant fuzzy set using multi-criteria decision making. Complex Intelligent Systems, 9(6), 6681-6695.
[10] Prasad, P., Madhav, V., Lal, R., Ravi, V. (2021). Optimal technical indicator-based trading strategies using nsga-ii. arXiv preprint arXiv:2111.13364.
[11] Kumar, P., Sharma, D. (2023). Benchmarking the financial performance of Indian commercial banks by a hybrid MCDM approach. International Journal of Process Management and Benchmarking, 15(3), 285-309. 
[12] Manish, Kumar, S. (2025). Stock selection with intuitionistic fuzzy combined compromise solutions. 
[13] Olmez, A. E. (2025). An Explainable Walk-Forward and Bootstrap Backtesting Framework for SPY Equity Strategy Development. Available at SSRN 5351507. 
[14] M. Pisal, A. Jain, and U. Rathod, Hybrid MCDM using TOPSIS and ARAS for financial evaluation, Scientific Reports, 2025.
[15] Refining and Robust Backtesting of A Century of Profitable Strategies, arXiv, 2024. 
[16] O. Salman, Optimization of Trading Strategies Using GA, PhD Thesis, University Repository, 2024. 
[17] Salman, O., Melissourgos, T., Kampouridis, M. (2023, July). Optimization of trading strategies using a genetic algorithm under the directional changes paradigm with multiple thresholds. In 2023 IEEE Congress on Evolutionary Computation(CEC) (pp. 1-8). IEEE. 
[18] Suvitha, K., Narayanamoorthy, S., Pamucar, D., Kang, D. (2024). An ideal plastic waste management system based on an enhanced MCDM technique. Artificial Intelligence Review, 57(4), 96. 
[19] Wahyuddin, E. P., Caraka, R. E., Kurniawan, R., Caesarendra, W., Gio, P. U., Pardamean, B. (2025). Improved LSTM hyperparameters alongside sentiment walk-forward validation for time series prediction. Journal of Open Innovation: Technology, Market, and Complexity, 11(1), 100458. 
[20] Jafari, H., Tabei, E. S., & Aqababaei Dehkordi, D., "Presenting a mathematical approach to developing the internal rate of return method: An application of Horner’s theorem in econometrics,"Mathematics and Computational Sciences, 6(3), 33–48, 2025.
[21] Mirabi, M., Ghaneai, H., Mousavi, S., Tavakoli, H. (2024). Bitcoin price forecasting using hybrid genetic algorithm. Mathematics and Computational Sciences, 5(2), 34-48. 
Mathematics and Computational Sciences
Volume 6, Issue 4
Autumn 2025
Pages 89-100

  • Receive Date 22 October 2025
  • Revise Date 26 November 2025
  • Accept Date 28 November 2025

Home

Submit Manuscript

Reviewers

Contact Us