<![CDATA[For vocational high school students, choosing a college major is crucial because it affects career suitability, skill development, and academic motivation. This study developed a hybrid recommendation system for students at Telkom Jakarta Vocational High School who are majoring in computer and network engineering and software engineering. This system combines rule-based matching for domain-based re-ranking, FAISS for vector similarity search, and Sentence-Transformers for semantic representation. Free-form text is used to represent students’ varied interests, preferences, hobbies, vocational skills, and report card grades. FAISS is used to index and convert the main descriptions into embeddings. Subsequently, the majors targeted by prospective students are re-ranked based on academic requirements, interest keywords, and competency linearity rules. Usability questionnaires and labeled data testing were used in the evaluation. The system achieved a Precision, Recall, and F1-Score of 0.8333 in a Top-3 scenario without report cards. The third metric was 0.7667 with report cards. This prototype is fairly easy to use and understand, based on an average SUS score of 69.57]]>
Copyrights © 2026
