A fuzzy logic-based multi-criteria decision-making framework for postgraduate candidate evaluation and selection

Postgraduate candidate selection is a complex multi-criterion decision-making (MCDM) problem involving both quantitative academic indicators and qualitative assessments. Traditional evaluation methods often rely on rigid scoring systems that inadequately address uncertainty, subjectivity, and imprecision in human judgments. To overcome these limitations, this study proposes a Fuzzy Logic-Based Multi-Criteria Decision Framework for the selection of postgraduate candidates. The proposed model integrates key admission criteria, including Grade Point Average (GPA), research potential, and interview performance, and represents them as linguistic variables to handle ambiguity in evaluation effectively. A Mamdani-type fuzzy inference system is employed to model expert decision rules and generate final candidate scores. The framework enhances interpretability by providing transparent rule-based reasoning that aligns with human expert judgment. Experimental analysis demonstrates that the fuzzy-based approach yields more consistent and reliable rankings than conventional weighted scoring techniques, particularly under uncertain or incomplete input conditions. The results highlight the model’s ability to improve fairness, robustness, and discrimination among candidates. This study contributes an interpretable and scalable decision-support tool that can assist academic institutions in making more transparent and data-driven postgraduate admission decisions while preserving human oversight.