Decision support system for VARK learning style recommendation using AHP and SAW methods

Abstract

To establish an objective mechanism for recommending tailored educational approaches, this research focuses on the architectural design of a DSS grounded in the VARK framework, which classifies preferences into visual, auditory, textual, and physical modalities. The operational framework combines AHP and SAW to eliminate subjectivity from the evaluation process. While the extraction of criteria importance factors relied on AHP, utilizing qualitative insights from a psychometrics expert in the field of psychology, the subsequent prioritization of pedagogical options was executed via SAW. Four core dimensions formed the basis of this evaluation, specifically focusing on how individuals perceive stimuli, process information, select instructional materials, and adapt to environmental settings. The initial matrix derivation yielded uniform importance coefficients of 0.25 across all dimensions, supported by a CR of 0 to verify the logical coherence of the expert input. Structurally, the platform was deployed as a responsive web system powered by the Laravel architecture and backed by a MySQL database engine. To confirm computational integrity, the algorithmic outputs generated by the software were audited against traditional manual calculations, resulting in a perfect mathematical alignment. Consequently, the empirical evidence confirms that the engineered DSS offers a precise diagnostic tool, thereby enabling learners to discover optimal educational pathways that correspond directly with their psychological profiles.