Intelligent Career Recommendation and Personalized Career Guidance System

I show the design of a career recommendation and personalized guidance system that uses NLP and machine-learning-based matching. This workflow takes user data and free-text descriptions builds a combined profile compares the combined profile with career descriptions and returns ranked options with reasons and potential skill gaps. TF-IDF with cosine similarity offers a starting point while sentence embeddings can be checked as an optional semantic approach. A rule-based baseline and a transparent evaluation plan are added to support a comparison. I note that the current manuscript describes a proposed system than a validated deployed solution. I cannot confirm the effectiveness of the career recommendation and personalized guidance system until the career catalogue is ready, the prototype is built and the planned evaluation is finished. Future work can bring an regularly updated career catalogue, feedback from students and career counsellors, multilingual input, better skill extraction and a more detailed learning-resource mapping. I also think further work should look at privacy, fairness, explainability and how users interpret the recommendations.

[1] C. Lahoud, S. Moussa, C. Obeid, H. El Khoury, et al., “A Comparative Analysis of Different Recommender Systems for University Major and Career Domain Guidance,” Education and Information Technologies, vol. 28, pp. 8733–8759, 2023. https://doi.org/10.1007/s10639-022-11541-3 [2] Y. Sarmurzin, A. Azhenov, A. Kudysheva, B. Ualikhanova, I. Saparbekova, and A. Besbayev, “Implementation of AI in Career Counselling for University Students: A Systematic Review,” Frontiers in Education, vol. 11, article 1787689, 2026. https://doi.org/10.3389/feduc.2026.1787689[3] C. D. Manning, P. Raghavan, and H. Schütze, Introduction to Information Retrieval. Cambridge University Press, 2008. https://nlp.stanford.edu/IR-book/ [4] N. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks,” in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3982–3992, 2019. https://doi.org/10.18653/v1/D19-1410 [5] A. José-García, A. Sneyd, A. Melro, A. Ollagnier, G. Tarling, H. Zhang, M. Stevenson, R. Everson, and R. Arthur, “C3-IoC: A Career Guidance System for Assessing Student Skills using Machine Learning and Network Visualisation,” International Journal of Artificial Intelligence in Education, vol. 33, pp. 1092–1119, 2023. https://doi.org/10.1007/s40593-022-00317-y [6] U.S. Department of Labor, “The O*NET Content Model,” O*NET Resource Center. https://www.onetcenter.org/content.html [7] European Commission, “European Skills, Competences, Qualifications and Occupations (ESCO): Use ESCO Services.” https://esco.ec.europa.eu/en/use-esco [8] S. Sarsenbay, I. Varlamis, C. Turan, B. Razhametov, and Y. Kazym, “Optimizing Academic Trajectories: A Multi-Dimensional Psychometric Recommender System for Student Career Guidance,” Informatics, vol. 13, no. 6, article 81, 2026. https://doi.org/10.3390/informatics13060081 [9] X. Xu and H. Gao, “A knowledge graph-integrated recommendation method for college student career planning,” Discover Artificial Intelligence, vol. 6, article 406, 2026. https://doi.org/10.1007/s44163-026-00996-9 [10] Manganello, F., Rasca, E., Villa, A., Maddalena, A., and Boccuzzi, G. (2025). “Machine learning for post-diploma educational and career guidance: a scoping review in AI-driven decision support systems.” Frontiers in Education, 10. https://doi.org/10.3389/feduc.2025.1578979