Fuzzy Inference and Explainable Artificial Intelligence for Mapping Multi-Dimensional Academic Performance to Technical Demand
TL;DR
This work offers a robust decision-support framework for higher education institutions, accreditation bodies, and employers by systematically linking graduates’ knowledge, skills, and behavioral attributes to technical demand by systematically linking graduates’ knowledge, skills, and behavioral attributes to technical demand.
Abstract
Assessing graduate students’ academic performance is a multifaceted task that requires consideration of both quantitative metrics and qualitative evaluations. Conventional assessment approaches rely on numerical scores and strict grading schemes, often neglecting critical soft factors such as student behavior, classroom participation, learning consistency, and extracurricular engagement. To address the ambiguity and imprecision inherent in human-centric evaluation, this work proposes an Explainable Artificial Intelligence (XAI) approach to produce a transparent, interpretable estimate of graduates’ technical demand. In the first phase, a fuzzy logic inference system was developed that considers academic scores, project outcomes, research productivity, the desired graduate outcome index, and qualitative feedback to produce a comprehensive assessment of graduate performance. The fuzzy model was developed using expert insights, supported by empirical analysis of anonymized academic data from graduates of the 2023-25 cohorts. The fuzzy system was developed using both Python and MATLAB and later deployed as a web-based application to provide real-time decision support for mapping educational outcomes to graduate employability. In the second phase, validated data from 1,875 students were used to build an explainable machine learning model using the no-code KNIME analytics platform. A Random Forest classifier, augmented with SHAP-based explainability, was employed to provide both global and local interpretations of student performance. The proposed model achieved an accuracy of 99.57% with Cohen’s kappa of 0.933, demonstrating strong predictive reliability and interpretability. This work offers a robust decision-support framework for higher education institutions, accreditation bodies, and employers by systematically linking graduates’ knowledge, skills, and behavioral attributes to technical demand.