An ESCO-Based Skill-Gap Detection Framework for SMEs: A Design Science Prototype of an Intelligent Learning Management System

The growing misalignment between workforce competences and the skill requirements of digitally evolving occupations is a critical barrier to SME competitiveness in the Industry 4.0 and 5.0 transitions. This study develops and demonstrates, through a working prototype, an ESCO-aligned analytical framework for skill-gap detection and adaptive reskilling, produced within the LUCE (LUtech Campus Ecosystem) project. Its contribution is theoretical, methodological, and technological rather than purely applicative. Drawing on human capital theory, the knowledge-based view of the firm, and skill-biased technical change, it conceptualizes reskilling as the relaxation of a firm-level human-capital–technology complementarity constraint, using ESCO to render this constraint observable and commensurable across firms. Methodologically, it defines the skill gap as a standardized, ontology-grounded measure; technologically, it integrates functions usually kept separate — performance analytics, skill assessment, and learning provision — into a single pipeline, instantiated as a proof-of-concept Intelligent Learning Management System. Workforce competences are extracted from anonymized employee CVs via a deterministic, rule-based Natural Language Processing procedure, mapped to ESCO preferred labels, alternative labels, and concept URIs, and linked to occupational requirements through occupation–skill relations. A Skill Gap Indicator, defined as the complement of evidenced ESCO competence coverage, yields a mean of 0.956, interpreted as a conservative upper-bound estimate rather than a literal measure of absent competences. The prototype then translates detected gaps into targeted training recommendations. As a research prototype, the system is validated along its technical and analytical dimensions rather than for training effectiveness; the relationship between gap closure and firm performance is advanced as a proposition for future longitudinal evaluation.