Application of the K-Means Algorithm in Enhancing the Clustering Model for Job Seekers in Cirebon City

The development of information technology opens up opportunities to improve the efficiency of job search through the grouping of job seekers based on specific characteristics. This study uses the K-Means algorithm to analyze data on job seekers in Cirebon City for 2018–2022, focusing on education level and gender. The stages of the research include (1) data selection, (2) data preprocessing, (3) transformation of attributes into numerical format, (4) data grouping using RapidMiner, and (5) evaluation of clustering results using the Davies-Bouldin Index (DBI). The results showed that the optimal number of clusters was two (K=2), with a DBI value of 0.608 which indicates good cluster separation. The first cluster consists of job seekers with a higher level of education, while the second cluster has a lower level of education. Gender did not show a significant influence. These findings provide strategic insights for governments and companies in developing data-driven policies, such as more effective training or recruitment programs. The K-Means algorithm has proven its potential in supporting strategic decision-making in workforce management and being adaptable to other regions.