A probabilistic approach to portfolio selection with risk-aversion coefficients estimated via logistic regression

Document Type : Research Article

Authors

Liem Chin

Agus Sukmana

Erwinna Chendra

Andreas Parama Wijaya

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

10.22067/ijnao.2026.95106.1716

Abstract

This work presents a probabilistic risk-aversion approach to portfolio selection that combines a logistic regression-based risk assessment framework with a mixed-integer optimization algorithm with mean semi-absolute deviation (MSAD) as the risk criterion. It allows us to incorporate uncertainty in the portfolio selection analysis as well as performance analysis by Monte Carlo simulation and compares the portfolios with different levels of risk over time instead of applying a deterministic system of selection based on historical data. The technical indicators of the LQ45 index predict the risk-aversion coefficient and can steer the model to the direction of the market. Under cardinality, quantity, and liquidity constraints, seven portfolios constructed from major Indonesian stock indices can be optimized with a Branch-and-Bound method that operates in GEKKO Python. Simulation results on 10,000 runs are taken to give the portfolios probabilistic rankings of return and risk. The probability values computed using the Monte Carlo method are plotted against the sample size to illustrate the convergence behavior of the algorithm. Eventually, to evaluate the robustness of the algorithm, variations in the probability values are examined by adding normally distributed noise into the model input parameters.

Keywords

Logistic regression

Mean semi-absolute deviation

Monte-Carlo simulation

Portfolio selection

Risk-aversion coefficients

Subjects

• Optimization

---

References

[1] Anagnostopoulos, K.P. and Mamanis, G. The mean-variance cardinality constrained port-
folio optimization problem: An experimental evaluation of five multiobjective evolutionary
algorithms, Expert Syst. Appl. 38 (2011), 14208–14217.
[2] Bindu, K.H, Mukkamala, R., Dey, N. and Rao, C. R. Coefficient of variation and machine
learning applications, CRC Press, 2019.
[3] Cesarone, F., Scozzari, A. and Tardella, F. A new method for mean-variance portfolio
optimization with cardinality constraints, Ann. Oper. Res. 205 (2013), 213–234.
[4] Fang, Y., Lai, K. K. and Wang, S.Y. Portfolio rebalancing model with transaction
costs based on fuzzy decision theory, Eur. J. Oper. Res. 175(2) (2006), 879–893.
https://doi.org/10.1016/j.ejor.2005.05.020
[5] Glasserman, P. Monte Carlo methods in Financial Engineering, Springer. (2003), 1–3.
[6] Grant, A., Kwon, O. K. and Satchell, S. Properties of risk aversion estimated from portfolio
weights, J. Asset Manag. 25 (2024), 427–444.
[7] James, G., Witten, D., Hastie, T., Tibshirani, R. and Taylor, J. An introduction to statistical
learning with applications in Python, Springer. (2023), 138–144.
[8] Ji, R., Lejeune, M.A. and Prasad, S.Y. Properties, formulations, and algorithms for portfolio
optimization using Mean-Gini criteria, Ann. Oper. Res. 248 (2017), 305–343.

[9] Jiang, Z., Ji, R. and Chang, K. C. A machine learning integrated portfolio rebalance frame-
work with risk-aversion adjustment, J. Risk Financial Manag. 13(7) (2020), 155.
[10] Konno, H. and Wijayanayake, A. Mean-absolute deviation portfolio optimization model un-
der transaction costs, J. Oper. Res. Soc. Jpn. 42(4) (1999), 422–435.
[11] Konno, H. and Yamazaki, H. Mean-absolute deviation portfolio optimization model and its
applications to Tokyo Stock Market, Manag. Sci. 37(5) (1991), 519–531.
[12] Lee, J. A first course in combinatorial optimization, Cambridge University Press: New York,
United States of America. (2004), 177–180.
[13] Markowitz, H. Portfolio selection, J. Finance. 7(1) (1952), 77-91.
[14] Mousavi, A. and Michailidis, G. Cardinality constrained mean-variance portfolios: a penalty
decomposition algorithm, Comput. Optim. Appl. 90 (2025), 631–648.
[15] Shadabfar, M. and Cheng, L. Probabilistic approach for optimal portfolio selection using a
hybrid Monte Carlo simulation and Markowitz model, Alex. Eng. J. 59 (2020), 3381–3393.
[16] Shadabfar, M. and Wang, Y. Approximation of the Monte Carlo sampling method for reli-
ability analysis of structures, Math. Probl. Eng. 2016(1) (2016), 5726565.
[17] Simaan, Y. Estimation risk in portfolio selection: The mean variance model versus the mean
absolute deviation model, Manag. Sci. 43(10) (1997), 1437–1446.
[18] Sortino, F. A. and Meer, R.v.d. Downside risk: Capturing what’s at stake in investment
situations, J. Portf. Manag. 17(4) (1991), 27–31.
[19] Xiaoxia, H. Portfolio analysis: from probabilistic to credibilistic and uncertain approaches,
Springer. (2010), 11–60.
[20] Yaman, I. and Dalkılıç, T. E. A hybrid approach to cardinality constraint portfolio selection
problem based on nonlinear neural network and genetic algorithm, Expert Syst. Appl. 169
(2021), 114517, 294–305.
[21] Yixuan, L. and Zhongfeng, Q. Mean semi-absolute deviation for uncertain portfolio opti-
mization problem, J. Uncertain Syst. 6(4) (2021), 299–307.
[22] Yufei, S., Grace, A., Lay, T. K., Guanglu, Z. Portfolio optimization using a new probabilistic
risk measure, J. Ind. Manag. Optim. 11(4) (2015), 1275–1283

[23] https://www.idx.co.id/id/data-pasar/data-saham/indeks-saham, last accessed July 24,
2025