Portfolio Optimization with a Multi-Objective Weighted Fuzzy Goal Programming Approach

Akba S., Dalkilic T., Akba Y.

ECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH, cilt.60, sa.3, ss.250-273, 2026 (SCI-Expanded, SSCI, Scopus)

Özet

Technological developments and increasing complexity in financial markets have highlighted the need to consider various financial criteria in addition to risk and return in portfolio management. This study proposes a portfolio selection model integrating the CRITIC method with Multi-Objective Weighted Fuzzy Goal Programming. Criterion weights are determined using CRITIC by considering the variability of each criterion and the correlations among criteria. The criteria are then formulated as fuzzy goals, and membership functions are constructed using target and tolerance values to represent uncertainty. The CRITIC weights are incorporated into the fuzzy goal programming model, while different values of the theta parameter are used to generate alternative portfolio allocations. The proposed approach is applied to NASDAQ-100 stocks and compared with CVaR, Mean-Variance, and ASM methods. Performance is evaluated using portfolio returns, Sharpe and Sortino ratios, and rolling-window analysis. The results show that the proposed method provides favorable performance compared with the other portfolio optimization methods in terms of both returns and risk-adjusted performance. Overall, the findings indicate that the proposed model provides an effective and applicable approach to multi-criteria portfolio selection under uncertainty.