Data-Driven Insights for Higher Education Marketing: Segmenting Applicant Pools Using K-Means Clustering

This research aims to optimize marketing strategies for new student recruitment at Bina Insani University (BiU), which faces intense competition. The current marketing efforts are generic and inefficient. Utilizing the CRISP-DM framework, this study applies the K-Means clustering data mining method to analyze primary data from applicants from 2021 to 2024. The analysis focuses on the attributes of previous school major, information source, and location. The findings successfully identified four distinct segments of prospective students: the "Proactive Outreach Segment," reached through school presentations; the "Social Network & Affiliation Segment," influenced by friends and relatives; the "Academic Recommendation Segment," who rely on guidance from teachers; and the "Digital & Non-Technical Segment," who actively seek information on social media. Based on the unique profile of each cluster, this study provides recommendations for specific and targeted marketing strategies to improve the effectiveness and efficiency of student recruitment