<![CDATA[In an increasingly competitive world of work, companies are required to have a fast, efficient, and objective employee selection process to get the best candidates. However, the high number of job applicants often causes the administrative selection process to be slow, inefficient, and prone to subjective errors in assessment. Therefore, a technology-based solution is needed that is able to systematically classify job applicants based on relevant criteria. This study proposes the application of the K-Means Clustering method to group job applicants based on three main variables, namely last education, work experience, and selection test scores. A total of 20 applicant data were analyzed using the K-Means algorithm with the stages of initial centroid initialization, Euclidean distance calculation, and iteration until the convergence point was reached. The results of the grouping resulted in three main categories: prioritized, considered, and doubtful applicants. Each group has its own characteristics that can help the HRD team in compiling a more selective and accurate list of candidates. This system is implemented in the form of a web-based recruitment platform that makes it easier for companies to conduct early selection automatically, structured, and data-based. The use of this method also increases accuracy and transparency in decision-making and reduces the potential for bias that often occurs in manual selection. These findings prove that K-Means Clustering is an effective and applicable method to support strategic decision-making in the field of human resources, especially in the early stages of employee selection. Additionally, this method can be easily adapted to the needs of other companies that have different selection criteria, making it flexible and widely applicable. The potential for the development of this system is also open to integration with other technologies such as machine learning or big data analytics in the future.]]>
