Data-Driven Innovation in Workforce Selection: A Clustering-Based Workflow for Technology Adoption in Indonesian Construction SMEs

Recruitment represents a critical socio-economic process that shapes labor market outcomes and organizational performance, especially for small and medium-sized enterprises (SMEs) operating in the construction sector. This study demonstrates how a data-driven and computational approach—using K-Means clustering—can support transparent, efficient, and innovation-oriented recruitment. A dataset of 30 shortlisted applicants from Indonesian construction consulting SMEs was evaluated across three competencies: AutoCAD drafting, report writing, and adaptability. The clustering process classified candidates into _Rejected_, _Under Consideration_, and _Accepted_ groups, with validity supported by a Davies–Bouldin Index of 0.41. Unlike threshold-based evaluations, clustering reveals nuanced groupings across technical and soft skills, enabling more precise and fair workforce selection. Conceptually, this work contributes to innovation management in SMEs by illustrating how data-driven decision tools can enhance human capital selection, reduce bias, and promote technology adoption for better workforce planning.