Hybrid Recom Hybrid Recommendation System for University Major Selection Using Sentence-Transformers, FAISS, and Rule-Based Matching Study Case at SMK Telkom Jakarta

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

Keywords: major recommendation, FAISS, rule-based matching, semantic similarity, Sentence- Transformers

[1] V. Nayak and N. Vora, “A Machine Learning-based Career Recommendation,” Journal of Trends in Computer Science and Smart Technology, vol. 6, no. 4, pp. 374–390, Dec. 2024, doi: 10.36548/jtcsst.2024.4.004.

[2] T. Amelia, Prajoko, and A. Pambudi, "Rekomendasi Jurusan Kuliah Berdasarkan Minat dan Kemampuan Menggunakan Metode Content Based Filtering," Technologia: Jurnal Ilmiah, vol. 14, no. 3, pp. 245–253, 2023, doi: 10.31602/tji.v14i3.11336.

[3] C. Lahoud, S. Moussa, C. Obeid, H. El Khoury, and P. A. Champin, “A comparative analysis of different recommender systems for university major and career domain guidance,” Educ. Inf. Technol. (Dordr)., vol. 28, no. 7, pp. 8733–8759, Jul. 2023, doi: 10.1007/s10639-022-11541-3.

[4] D. Ramadhan and L. Marlinda, “Decision Support System for selecting study programs using the AHP method,” Sinkron, vol. 7, no. 4, pp. 2547–2555, Oct. 2022, doi: 10.33395/sinkron.v7i4.11821.

[5] L. Guder, J. P. Aires, H. U. da Silva, F. Meneguzzi, and D. Griebler, "Sentence Representations for Semantic Textual Similarity: A Systematic Review," Computer Speech & Language, vol. 100, Art. no. 101970, 2026, doi: 10.1016/j.csl.2026.101970.

[6] M. Douze et al., "The FAISS Library," IEEE Transactions on Big Data, 2025, doi: 10.1109/TBDATA.2025.3618474.

[7] H. Jégou, M. Douze, and C. Schmid, “Product quantization for nearest neighbor search,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 1, pp. 117–128, 2011, doi: 10.1109/TPAMI.2010.57.

[8] M. Guesmi, M. A. Chatti, L. Kadhim, S. Joarder, and Q. U. Ain, “Semantic Interest Modeling and Content-Based Scientific Publication Recommendation Using Word Embeddings and Sentence Encoders,” Multimodal Technologies and Interaction, vol. 7, no. 9, Sep. 2023, doi: 10.3390/mti7090091.

[9] T. C. Uzoma, C. O. Ikerionwu, M. E. Nwanga, and C. Etus, “Machine Learning Recommender System for an Enhanced Students Course Selection,” International Journal of Computer Trends and Technology, vol. 72, no. 10, pp. 31–35, Oct. 2024, doi: 10.14445/22312803/ijctt-v72i10p106.

[10] A. Jadon and A. Patil, "A Comprehensive Survey of Evaluation Techniques for Recommendation Systems," arXiv preprint arXiv:2312.16015, 2024.

[11] N. Kamal, F. Sarker, A. Rahman, S. Hossain, and K. A. Mamun, “Recommender System in Academic Choices of Higher Education: A Systematic Review,” IEEE Access, vol. 12, pp. 35475–35501, 2024, doi: 10.1109/ACCESS.2024.3368058.

[12] K. Crandall, K. S. Crandall, and M. North, "A Decade Perspective of Recommender Systems Research: A Systematic Review," Issues in Information Systems, vol. 25, no. 3, pp. 496–507, 2024.

[13] M. Aucancela, A. González Briones, and P. Chamoso, "Educational Recommender Systems: A Systematic Literature Review," in The Barcelona Conference on Education 2023: Official Conference Proceedings, 2023, pp. 933–951, doi: 10.22492/issn.2435-9467.2023.74.

[14] F. L. da Silva, B. K. Slodkowski, K. K. A. da Silva, and S. C. Cazella, “A systematic literature review on educational recommender systems for teaching and learning: research trends, limitations and opportunities,” Educ. Inf. Technol. (Dordr)., vol. 28, no. 3, pp. 3289–3328, Mar. 2023, doi: 10.1007/s10639-022-11341-9.

[15] K. Khatimah and M. A. Gustalika, “Implementation of A Decision Support System for Major Selection using AHP and TOPSIS Method,” Building of Informatics, Technology and Science (BITS), vol. 6, no. 1, Jun. 2024, doi: 10.47065/bits.v6i1.5256.

[16] S. El-Keiey, D. ElMenshawy, and E. Hassanein, "Career Recommendation Based on Feature Selection for Undergraduate Students Using Machine Learning Techniques," International Journal of Advanced Computer Science and Applications (IJACSA), vol. 16, no. 3, pp. 234–244, 2025, doi: 10.14569/IJACSA.2025.0160323.

[17] Y. Han, C. Liu, P. Wang, J. Huang, and B. Li, "A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge," arXiv preprint arXiv:2310.11703, 2023, doi: 10.48550/arXiv.2310.11703.

[18] H. Liu, A. Gegov, and M. Cocea, “Rule-based systems: a granular computing perspective,” Granular Computing, vol. 1, no. 4, pp. 259–274, Dec. 2016, doi: 10.1007/s41066-016-0021-6.

[19] M. Siino, I. Tinnirello, and M. La Cascia, “Is text preprocessing still worth the time? A comparative survey on the influence of popular preprocessing methods on Transformers and traditional classifiers,” Inf. Syst., vol. 121, Mar. 2024, doi: 10.1016/j.is.2023.102342.

[20] Z. Miao, Q. Wu, K. Zhao, Z. Wu, and Y. Tsuruoka, "Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment," in Findings of the Association for Computational Linguistics: NAACL 2024, 2024, pp. 3225–3236, doi: 10.18653/v1/2024.findings-naacl.20.

[21] M. Danish, S. I. Ansarullah, S. Khan, and S. Alshmrany, “A Sentiment-Aware and Explainable Hybrid Recommender System Based on Ratings and Transformer Embeddings,” International Journal of Computational Intelligence Systems, vol. 19, no. 1, Dec. 2026, doi: 10.1007/s44196-026-01305-z.

[22] M. Abbad, R. Alfath, and A. N. Rohman, "Content-Based Filtering Recommendation System for E-Commerce Products Using Sentence-BERT and Cosine Similarity," Journal of Applied Informatics and Computing, 2026.

[23] A. Klimashevskaia, D. Jannach, M. Elahi, and C. Trattner, “A survey on popularity bias in recommender systems,” User Model. User-adapt. Interact., vol. 34, no. 5, pp. 1777–1834, Nov. 2024, doi: 10.1007/s11257-024-09406-0.

[24] J. Aisyiah, M. Risnasari, and A. T. Ni'mah, "Sistem Rekomendasi Program Studi Menggunakan Metode Hybrid Recommendation (Studi Kasus: MAN Sumenep)," Journal of Education and Informatics Research, vol. 4, no. 1, 2023.

[25] I. Lubis, H. Lubis, and I. Nur Wahidah, “Implementation of Semantic Search in an Academic Repository Using Sentence-BERT and FAISS,” sinkron, vol. 10, no. 2, pp. 1060–1069, Apr. 2026, doi: 10.33395/sinkron.v10i2.15940.