Multi-objective portfolio optimization using real coded genetic algorithm based support vector machines

Document Type : Research Article

Authors

• B. Surja
• L. Chin
• F. Kusnadi

Center for Mathematics and Society, Department of Mathematics, Faculty of Science, Parahyangan Catholic University, Bandung, Indonesia.

10.22067/ijnao.2025.89520.1499

Abstract

Investors need to grasp how liquidity affects both risk and return in order to optimize their portfolio performance. There are three classes of stocks that accommodate those criteria: Liquid, high-yield, and less-risky. Classifying stocks help investors build portfolios that align with their risk profiles and investment goals, in which the model was constructed using the one-versus-one support vector machines method with a radial basis function kernel. This model was trained using a combination of the Kompas100 index and the Indonesian industrial sectors stocks data. Single optimal portfolios were created using the real coded genetic algorithm based on different sets of objectives: Maximizing short-term and long-term returns, maximizing liquidity, and minimizing risk. In conclusion, portfolios with a balance on all these four investment objectives yielded better results compared to those focused on partial objectives. Furthermore, our proposed method for selecting portfolios of top-performing stocks across all criteria outperformed the approach of choosing top stocks based on a single criterion.

Keywords

• Genetic algorithm
• Liquidity
• Multi-objective optimization
• One-versus-one support vector machines
• Radial basis functions

Main Subjects

• Optimization

---

References

[1] Awad, M., and Khanna, R. Efficient learning machines: Theories, con-cepts, and applications for engineers and system designers. Springer Na-ture, New York, 2015.
[2] Bali, T.G., Peng, L., Shen, Y., and Tang, Y. Liquidity shocks and stock market reactions, Rev. Financ. Stud. 27(5) (2014) 1434–1485.
[3] Beardsley, X.W., Field, B., and Xiao, M. Mean-variance-skewness-kurtosis portfolio optimization with return and liquidity, Commun. Math. Financ. 1(1) (2012) 13–49.
[4] Chen, J.S., Hou, J.L., Wu, S.M., and Chang-Chien, Y.W. Constructing investment strategy portfolios by combination genetic algorithms, Expert Syst. Appl. 36(2) (2009) 3824–3828.
[5] Chen, W., Wang, Y., Gupta, P., and Mehlawat, M.K. A novel hybrid heuristic algorithm for a new uncertain mean-variance-skewness portfolio selection model with real constraints, Appl. Intell. 48 (2018) 2996–3018.

[6] Chordia, T., Roll, R., and Subrahmanyam, A. Liquidity and market efficiency, Journal of Financial Economics, 87(2) (2008) 249–268.
[7] Fabozzi, F.J., Gupta, F., and Markowitz, H.M. The legacy of modern portfolio theory, J. Invest. 11(3) (2002) 7–22.
[8] Fan, A., and Palaniswami, M. Stock selection using support vector ma-chines, In International Joint Conference on Neural Networks. Proceed-ings, (Cat. No. 01CH37222) (2001) 1793–1798.
[9] Flach, P.Machine learning: The art and science of algorithms that make sense of data. Cambridge University Press, Cambridge, 2012.
[10] Guijarro, F. A similarity measure for the cardinality constrained frontier in the mean–variance optimization model, J. Oper. Res. Soc. 69(6) (2018) 928–945.
[11] Gupta, P., Mehlawat, M.K., Inuiguchi, M., and Chandra, S. Multi-criteria portfolio optimization using support vector machines and genetic algorithms, Studies in Fuzziness and Soft Computing, vol 316. (pp. 283–309) Springer, Berlin, Heidelberg, 2014.
[12] Gupta, P., Mehlawat, M.K., and Saxena, A. A hybrid approach to asset allocation with simultaneous consideration of suitability and optimality, Inf. Sci. 180(11) (2010) 2264–2285.
[13] Herrera, F., Lozano, M., and Verdegay, J.L. Tackling real-coded genetic algorithms: Operators and tools for behavioural analysis, Artif. Intell. Rev. 12 (1998) 265–319.
[14] Hsu, C.W., and Lin, C.J. A comparison of methods for multiclass support vector machines, IEEE Trans. Neural Networks Learn. Syst. 13(2) (2002) 415–425.
[15] Huang, C.F. A hybrid stock selection model using genetic algorithms and support vector regression, Appl. Soft Comput. 12(2) (2012) 807–818.
[16] Huang, Z., Chen, H., Hsu, C.J., Chen, W.H., and Wu, S. Credit rating analysis with support vector machines and neural networks: A market comparative study, Decis. Support Syst. 37(4) (2004) 543–558.

[17] Jimbo, H.C., Ngongo, I.S., Andjiga, N.G., Suzuki, T., and Onana, C.A. Portfolio optimization under cardinality constraints: A compar-ative study, Open J. Stat. 7(4) (2017) 731–742.
[18] Jin, Y., Qu, R., and Atkin, J. Constrained portfolio optimisation: The state-of-the-art markowitz models, In International Conference on Oper-ations Research and Enterprise Systems (2016) 388–395.
[19] Kessaci, Y. A multi-objective continuous genetic algorithm for finan-cial portfolio optimization problem, In Proceedings of the Genetic and Evolutionary Computation Conference Companion (2017) 151–152.
[20] Ma, Y., Han, R., and Wang, W. Portfolio optimization with return pre-diction using deep learning and machine learning, Expert Syst. Appl.165 (2021) 113973.
[21] Mitchell, M. An introduction to genetic algorithms. MIT Press, Cam-bridge, 1998.
[22] Mutunge, P., and Haugland, D. Minimizing the tracking error of car-dinality constrained portfolios, Computers and Operations Research, 90 (2018) 33–41.
[23] Packard, N.H. A genetic learning algorithm for the analysis of complex data, Complex Syst. 4(5) (1990) 543–572.
[24] Rather, A.M., Sastry, V.N., and Agarwal, A. Stock market prediction and portfolio selection models: A survey, Opsearch, 54 (2017) 558–579.
[25] Santoso, W., Harun, C.A., Hidayat, T., and Wonida, H. Market liquidity risk as an indicator of financial stability: The case of Indonesia, Bank of Indonesia, (2010). 1–22.
[26] Sheppard, C. Genetic algorithms with python. Smashwords Edition, Austin, TX, USA 2017.
[27] Vogel, H.L. Entertainment industry economics: A guide for financial analysis. Cambridge University Press, Cambridge, 2020 .

[28] Yu, L., Wang, S., and Lai, K.K. Neural network-based mean–variance–skewness model for portfolio selection, Comput. Oper. Res. 35(1) (2008) 34–46.
[29] Zhang, P. Multi-period possibilistic mean semivariance portfolio selection with cardinality constraints and its algorithm, J. Math. Model. Algor. Oper. Res. 14 (2015) 239–253.
[30] Zhang, P. An interval mean–average absolute deviation model for mul-tiperiod portfolio selection with risk control and cardinality constraints, Soft Comput. 20 (2016) 1203–1212.
[31] Zhang, P. Multiperiod mean absolute deviation uncertain portfolio selec-tion, Ind. Eng. Manag. Syst. 15(1) (2016) 63–76.
[32] Zhou, Z., Jin, Q., Xiao, H., Wu, Q., and Liu, W. Estimation of car-dinality constrained portfolio efficiency via segmented DEA, Omega, 76 (2018) 28–37.
[33] Zhou, Z., Liu, X., Xiao, H., Wu, S., and Liu, Y. A DEA-based MOEA/D algorithm for portfolio optimization, Clust. Comput. 22(Suppl 6) (2019) 14477–14486.