<![CDATA[The rapid development of digital technology and the growing need for personalized career guidance have driven the transformation of career counseling services in higher education. Many students still face difficulties in determining career paths that align with their interests, potential, and competencies. This issue is worsened by the limitations of conventional counseling services that are not yet data-driven. Therefore, this study develops a student career counseling platform based on digital profiling integrated with a recommendation system using Machine Learning. The research employed literature review and prototyping methodology. Student data (interests, academic performance, activities, and skills) were processed using Decision Tree and K-Nearest Neighbor (KNN) algorithms to generate relevant career-path recommendations. The results indicate that integrating digital profiling with a machine learning-based recommendation system enhances personalization, accuracy, and adaptability of career recommendations.]]>
Copyrights © 2026
