Penerapan K-Means Clustering untuk Mengidentifikasi Siswa Prioritas Penerima Beasiswa Berdasarkan Karakteristik Sosial-Ekonomi di SDI Teladan Saadatuddarain Jagakarsa

Abstrak

Scholarships are one form of targeted support to ensure that students are able to continue their education. Scholarship programs are not only intended to alleviate the financial burden of education, but also serve as a strategy to prevent school dropout rates and low-quality human resources. The design of a scholarship recipient determination system is required to map eligible students based on their Socio-Economic Status (SES), establish assistance priorities, and address limitations in scholarship quotas. The application of structured data analysis assists teachers and school staff in understanding students’ economic conditions more accurately, thereby enabling scholarships to be awarded in a more targeted and effective manner. The research methods employed include problem formulation, problem identification, literature review, analysis of problem-solving approaches, data collection, and observation. Meanwhile, the computational method utilizes the K-means clustering algorithm for data grouping and priority determination. The results of the study produced groups based on predefined characteristics, consisting of 12 students in the high-priority group, 20 students in the medium-priority group, and 18 students in the non-priority group, out of a total of 50 students. A system based on Socio-Economic Status (SES) characteristics—namely transportation, number of family dependents, and parents’ income—has proven capable of mapping students into high-, medium-, and non-priority groups, thereby assisting schools in determining scholarship recipients in a more precise and targeted manner.