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

In this paper, the authors investigate the potential of K-Means clustering as a tool to improve recruitment practices in Indonesian construction, speci cally for small and medium-sized enterprises (SMEs).The authors use a data-driven approach to classify candidates according to three main skills: AutoCAD drafting, report writing, and adaptability.K-Means clustering is a widely used unsupervised learning algorithm, known for its simplicity and scalability.One of the reasons for selecting K-Means is its effectiveness with small datasets, making it particularly suited to the SME context, where large volumes of data may not be available.Additionally, K-Means can ef ciently handle the three competencies evaluated in the study: technical skills (AutoCAD drafting), communication skills (report writing), and soft skills (adaptability).