Job Recommendation for Fresh Graduates to Reduce Competency Gaps Using Content-Based Filtering and Retrieval-Augmented Generation

Iftitah Yanuar Rahmawati; Felda Mufarihati; Christian Sri Kusuma Aditya

doi:10.52436/1.jutif.2026.7.2.5723

Authors

Iftitah Yanuar Rahmawati Informatics, Universitas Muhammadiyah Malang, Indonesia
Felda Mufarihati Informatics, Universitas Muhammadiyah Malang, Indonesia
Christian Sri Kusuma Aditya Informatics, Universitas Muhammadiyah Malang, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.2.5723

Keywords:

content-based filtering, explainable AI, retrieval-augmented generation, sentence-BERT, skill gap analysis

Abstract

Job recommendation systems are frequently used to help job seekers find suitable positions. Nevertheless, many existing systems focus primarily on accuracy and provide limited justification. This lack of openness can erode user confidence, particularly among recent grads who need a clear explanation of how their individual experiences fit the recommendations. Furthermore, these systems frequently lack sophisticated methods to explain the reasoning behind the recommendations, such as Retrieval-Augmented Generation (RAG), which makes them seem impersonal and difficult to trust. The purpose of this research is to develop an explainable job recommendation system that generates employment suggestions based on language comprehension by integrating RAG and Content-Based Filtering (CBF). User profiles and open positions are displayed using TF-IDF and Sentence-BERT, and then the experience level-based cosine similarity is calculated. To measure competency coverage, matching and absent skills are identified in an explicit skill-gap analysis. The Large Language Model and FAISS-based RAG modules leverage the explanations that are produced by finding matched and missing abilities as context. The CBF approach was used to evaluate recommendation relevance, while BLEU and ROUGE on ten test documents were used by HR specialists for validation. The system's mean ROUGE-1 F1 score was 0.4659, and its mean ROUGE-L score was 0.2918, based on 10 evaluation cases. Results show that the proposed recommendation system provides accurate and adequate guidelines based on HR references. This paper enriches Informatics by consolidating semantic similarity modeling, explicit competency-gap reasoning, and grounded text generation together to form a cohesive explainable recommendation framework targeted to cold-start job seekers.

Downloads

Download data is not yet available.

References

E. Mendez Guzman, V. Schlegel, and R. Batista-Navarro, “From outputs to insights: a survey of rationalization approaches for explainable text classification,” Frontiers in Artificial Intelligence, vol. 7, Art. no. 1363531, 2024, doi: 10.3389/frai.2024.1363531.

V. Anderson dan M. Tomlinson, “Signaling standout graduate employability: The employer perspective,” Human Resource Management Journal, vol. 31, no. 3, pp. 675–693, 2021, doi: 10.1111/1748-8583.12334.

A. Eimer and C. Bohndick, “Employability models for higher education: A systematic literature review and analysis,” Social Science & Humanity Open, vol. 8, no. 1, Art no. 100588, 2023, doi: 10.1016/j.ssaho.2023.100588.

C. Chalid, “Tingkat Kompetensi Mahasiswa Fresh Graduate dalam Menghadapi Persaingan Dunia Kerja,” Indones. J. Teach. Teach. Educ., vol. 1, no. 1, pp. 10–13, 2021, doi: 10.58835/ijtte.v1i1.58.

Badan Pusat Statistik (BPS), “Keadaan Angkatan Kerja di Indonesia Agustus 2025,” Badan Pusat Statistik (BPS), Jakarta, Indonesia, Statistik 04100.25018, Desember 2025. [Daring]. Tersedia pada: https://www.bps.go.id/id/publication/2025/12/19/42a75ee61332755586fdfcdd/keadaan-angkatan-kerja-di-indonesia-agustus-2025.html

D. Çelik Ertuğrul and S. Bitirim, “Job recommender systems: a systematic literature review, applications, open issues, and challenges,” Journal of Big Data, vol. 12, no. 1, pp. 140, 2025, doi: 10.1186/s40537-025-01173-y.

S. Sarsenbay, A. Kabdiyev, I. Varlamis, C. Sardianos, C. Turan, B. Razhametov, and Y. Kazym, “Generating job recommendations based on user personality and Gallup tests,” Algorithms, vol. 18, no. 5, Art. no. 275, 2025, doi: 10.3390/a18050275.

F. Tang, R. Zhu, F. Yao, J. Wang, L. Luo, and B. Li, “Explainable person–job recommendations: challenges, approaches, and comparative analysis,” Frontiers in Artificial Intelligence, vol. 8, Art. no. 1660548, 2025, doi: 10.3389/frai.2025.1660548.

J. Govea, R. Gutierrez, and W. Villegas-Ch, “Transparency and precision in the age of AI: evaluation of explainability-enhanced recommendation systems,” Frontiers in Artificial Intelligence, vol. 7, Art. no. 1410790, Sep 2024, doi: 10.3389/frai.2024.1410790.

A. Akkasi, “Job description parsing with explainable transformer-based ensemble models to extract the technical and non-technical skills,” Nat. Lang. Process. J., vol. 9, Art. no. 100102, 2024, doi: 10.1016/j.nlp.2024.100102.

C. Upadhyay, H. Abu-Rasheed, C. Weber, and M. Fathi, “Explainable Job-Posting Recommendations Using Knowledge Graphs and Named Entity Recognition,” dalam 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Melbourne, Australia: IEEE, 2021, pp. 3291–3296. doi: 10.1109/SMC52423.2021.9658757.

M. H. Hussein, A. A. Alsakaa, and H. A. Marhoon, “Adopting explicit and implicit social relations by SVD++ for recommendation system improvement,” TELKOMNIKA Telecommunication, Computing, Electronics and Control, vol. 19, no. 2, pp. 471, 2021, doi: 10.12928/telkomnika.v19i2.18149.

A. Rouf, Y. M. Pranoto, and E. Setyati, “Sistem Rekomendasi Pekerjaan Menggunakan Content Based Similarity,” JUTISI: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi, vol. 12, no. 2, pp. 618, 2023, doi: 10.35889/jutisi.v12i2.1229.

M. Rani, B. K. Mishra, D. Thakker, and M. N. Khan, “To Enhance Graph-Based Retrieval-Augmented Generation (RAG) with Robust Retrieval Techniques,” in Proceedings of the 2024 18th International Conference on Open Source Systems and Technologies (ICOSST), Lahore, Pakistan: IEEE, 2024, pp. 1–6. doi: 10.1109/ICOSST64562.2024.10871140.

W. Yuan, G. Neubig, and P. Liu, “BARTScore: Evaluating Generated Text as Text Generation,”, arXiv preprint arXiv:2106.11520, 2021, doi: 10.48550/ARXIV.2106.11520.

M. Zhong, Y. Liu, D. Yin, Y. Mao, Y. Jiao, P. Liu, et al., “Towards a Unified Multi-Dimensional Evaluator for Text Generation,” in Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, 2022, pp. 2023–2038, doi: 10.18653/v1/2022.emnlp-main.131.

Y. Liu, D. Iter, Y. Xu, S. Wang, R. Xu, and C. Zhu, “G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment,” in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore: Association for Computational Linguistics, 2023, pp. 2511–2522. doi: 10.18653/v1/2023.emnlp-main.153.

V. S. Pendyala, N. B. Thakur, and R. Agarwal, “Explainable Use of Foundation Models for Job Hiring,” Electronics, vol. 14, no. 14, Art. no. 2787, 2025, doi: 10.3390/electronics14142787.

R. Karlović, M. Rovis, A. Smajić, L. Sever, and I. Lorencin, “Context-Aware Tourism Recommendations Using Retrieval-Augmented Large Language Models and Semantic Re-Ranking,” Electronics, vol. 14, no. 22, Art. no. 4448, 2025, doi: 10.3390/electronics14224448.

A. Y. A. Ardhana, H. N. U. Syazeedah, R. I. Fitriyaningrum, and A. Gunawan, “Analisis Ketidaksesuaian antara Pendidikan dengan Kebutuhan Dunia Kerja di Indonesia,” Kompeten Jurnal Ilmiah Ekonomi dan Bisnis, vol. 3, no. 4, pp. 1020–1026, 2025, doi: 10.57141/kompeten.v3i4.156.

N. Yadav and D. Gopinathan, “Retrieval Augmented Generation Model for Paper Recommendation System,” SN Computer Science, vol. 6, no. 6, Art. no. 579, 2025, doi: 10.1007/s42979-025-04095-x.

S. He, Y. Zhao, Q. Li, and Y. Ma, “RGPRec: A RAG‐Enhanced GNN for Personalized Task Recommendations in Open‐Source Communities,” Software Practice and Experience, vol. 56, no. 1, pp. 3–25, 2026, doi: 10.1002/spe.70022.

L. M. De Campos, J. M. Fernández-Luna, and J. F. Huete, “An explainable content-based approach for recommender systems: a case study in journal recommendation for paper submission,” User Modelling and User-Adapted Interaction, vol. 34, no. 4, pp. 1431–1465, 2024, doi: 10.1007/s11257-024-09400-6.

S. Luo, J. Xu, X. Zhang, L. Wang, S. Liu, H. Hou, and L. Song, “RALLRec+: Retrieval-augmented large language model recommendation with reasoning,” Expert Systems with Applications, vol. 297, Art. no. 129508, 2026, doi: 10.1016/j.eswa.2025.129508.

J. Munson, T. Cuezze, S. Nesar, and D. Zosso, “A review of large language models and the recommendation task,” Discover Artificial Intelligence, vol. 5, no. 1, Art. no. 203, 2025, doi: 10.1007/s44163-025-00334-5.

F. G. F. Putranto, C. Natalia, and N. K. D. Pitriyani, “Closing the Gap Between Education and Labor Market Requirement: Do Vocational Education Matter?,” Journal Indonesian Sustainable Development Planning, vol. 5, no. 3, pp. 181–191, 2024, doi: 10.46456/jisdep.v5i3.614.

] P. Singla, “An Intelligent Job Recommendation System based on Semantic Embeddings and Machine Learning,” Journal of Information Systems Engineering and Management, vol. 10, no. 5s, pp. 520–542, 2025, doi: 10.52783/jisem.v10i5s.681.

A. N. Hasoon, S. K. Abdulateef, R. S. Abdulameer, and M. L. Shuwandy, “An Intelligent Hybrid AI Course Recommendation Framework Integrating BERT Embeddings and Random Forest Classification,” Computers, vol. 14, no. 9, Art. no. 353, 2025, doi: 10.3390/computers14090353.

Z. Guan, J.-Q. Yang, Y. Yang, H. Zhu, W. Li, and H. Xiong, “JobFormer: Skill-Aware Job Recommendation with Semantic-Enhanced Transformer,” ACM Transactions on Knowledge Discovery from Data, vol. 19, no. 1, pp. 1–20, 2025, doi: 10.1145/3701735.

M.-H. Ajjam and H. S. Al-Raweshidy, “AI-driven semantic similarity-based job matching framework for recruitment systems,” Information Science, vol. 724, Art. no. 122728, 2026, doi: 10.1016/j.ins.2025.122728.

M. P. Syah, Ajeng Puspa Wardani, Mohammad Idhom, and Trimono, “Perbandingan Representasi Teks Tf-Idf Dan Bert Terhadap Akurasi Cosine Similarity Dalam Penilaian Otomatis Jawaban Berbasis Teks,” Data Science Indonesia, vol. 5, no. 1, pp. 47–59, 2025, doi: 10.47709/dsi.v5i1.6021.

P. Aprilio, M. Felix, P. S. Nugraha, and H. Fahmi, “Hybrid Feature Combination of TF-IDF and BERT for Enhanced Information Retrieval Accuracy,” JISA: Jurnal Informatika dan Sains, vol. 8, no. 1, pp. 8–15, 2025, doi: 10.31326/jisa.v8i1.2179.

M. Klesel and H. F. Wittmann, “Retrieval-Augmented Generation (RAG),” Bussiness & Information Systems Engineering, vol. 67, no. 4, pp. 551–561, 2025, doi: 10.1007/s12599-025-00945-3.

A. Said, “On explaining recommendations with Large Language Models: a review,” Frontiers Big Data, vol. 7, Art. no. 1505284, 2025, doi: 10.3389/fdata.2024.1505284.

M. Yang, M. Zhu, Y. Wang, L. Chen, Y. Zhao, X. Wang, et al., "Fine-Tuning Large Language Model Based Explainable Recommendation with Explainable Quality Reward," Proceeding of the AAAI Conference on Artificial Intelligence, vol. 38, no. 8, pp. 9250-9259, 2024, doi: 10.1609/aaai.v38i8.28777.

M. Evtikhiev, E. Bogomolov, Y. Sokolov, and T. Bryksin, “Out of the BLEU: How should we assess quality of the Code Generation models?,” Journal of Systems and Software, vol. 203, Art. no. 111741, 2023, doi: 10.1016/j.jss.2023.111741.

M. Zhang, C. Li, M. Wan, X. Zhang, and Q. Zhao, “ROUGE-SEM: Better evaluation of summarization using ROUGE combined with semantics,” Expert Systems with Applications, vol. 237, Art. no 121364, 2024, doi: 10.1016/j.eswa.2023.121364.

A. Auriemma Citarella, M. Barbella, M. G. Ciobanu, F. De Marco, L. Di Biasi, and G. Tortora, “Assessing the effectiveness of ROUGE as unbiased metric in Extractive vs. Abstractive summarization techniques,” Journal of Computer Science, vol. 87, Art. no. 102571, 2025, doi: 10.1016/j.jocs.2025.102571.

X. Zhang, Y. Li, J. Wang, B. Sun, W. Ma, M. Zhang, et al., "Large Language Models as Evaluators for Recommendation Explanations," Proceedings of the 18th ACM Conference on Recommender Systems, Bari, Italy, 2024, pp. 33–42, doi: 10.1145/3640457.3688075.