This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Divyam Manchanda,
Ravikant Jangir,
Nikita Malik,
- Student, Dept. of Computer Applications, Maharaja Surajmal Institute, GGSIP University, Delhi, India
- Student, Dept. of Computer Applications, Maharaja Surajmal Institute, GGSIP University, Delhi, India
- Assistant professor, Dept. of Computer Applications, Maharaja Surajmal Institute, GGSIP University, Delhi, India
Abstract
The selection of suitable career has become very difficult and it’s complexity is being increased day by day, due to advancement in technology and number of professional fields. conventional approaches of suitable of occupation focus on aptitude tests that in fact do not consider the variability in skills. This paper introduces a new AI-powered career suggestion portal called Elevare, which attempted to help students choose a career occupation based on research. The main focus and purpose of this paper would be to develop a model that would be able to predict the occupation as well as provide a skill gap report. The proposed system includes the combination of a classification system based on the Random Forest model and a web-based system based on MERN stack using Python machine learning (ML) microservice. Student profile using academic background, technical skills and interests is analyzed using TF-IDF vectorization to be able to better predict the career in which they will fit. The efficacy of the proposed method in career prediction is proven by the practical analysis, which is much better than the traditional classification systems particularly in dealing with varying and specific career categories to work with. The proposed system also enhances the user experience through the conversion of career predictions into instructive activities in customized learning paths. Apart from career recommendations, users are also given dynamic roadmaps. The results show that Elevare serves to bridge this gap between the student potential and industry expectations in order to make career planning more structured, transparent and outcome – oriented.
Keywords: AI-based career recommendation, skill gap analysis, random forest classification, TF-IDF text vectorization, personalized learning roadmap, MERN stack with machine learning integration
References
- Zhang X, Liu S, Wang H. Personalized learning path recommendation for e-learning based on knowledge graph and graph convolutional network. International journal of software engineering and knowledge engineering. 2023 Jan 22;33(01):109-31.
- Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J. Scikit-learn: Machine learning in Python. the Journal of machine Learning research. 2011 Nov 1;12:2825-30.
- Nongnuch K, Piriyasurawong P. A deep learning-based career recommendation system using program learning outcomes and TPQI standards in the digital industry. Edelweiss Applied Science and Technology. 2025 July 16;9(7):1278–98. Available from: https://learning- gate.com/index.php/2576-8484/article/view/8898
- Skills Gap Analysis Tool: Visual Reports to Find & Fix Gaps Fast. Skills Base. 2026. Available from: https://www.skills-base.com/skills-gap-analysis-tool
- Li A, Li Y, Gao X. Personalized Learning Path Recommendation Based on Knowledge Graphs: A Survey. Electronics. 2026 Jan 5;15(1):238.
- Wu W, Yang S, Yi L, Wang H, Zhu G, Wang H. Knowledge Graph Enhanced Recommendation via Dynamic Fusion and Multi-Dimensional Contrastive Learning. In2025 7th International Conference on Frontier Technologies of Information and Computer (ICFTIC) 2025 Dec 5 (pp. 327- 333). IEEE.
- Jameson A, Willemsen MC, Felfernig A, De Gemmis M, Lops P, Semeraro G, Chen L. Human decision making and recommender systems. InRecommender systems handbook 2015 (pp. 611- 648). Boston, MA: Springer US.
- El-Keiey S, ElMenshawy D, Hassanein E. Career Recommendation Based on FeatureSelection for Undergraduate Students Using Machine Learning Techniques. International Journal of Advanced Computer Science & Applications. 2025 Mar 1;16(3).
- Gander M. The hybrid career concept: creating hybrid career pathways. Career Development International. 2021 Oct 22;26(7):853-68.
- Latha R, Sreenithi R. SKILL GAP ANALYSIS USING MACHINE LEARNING. International Journal of Engineering Research and Sustainable Technologies (IJERST). 2025 Sep 25;3(3):33-9.
- Bekkerman R, Gavish M. High-precision phrase-based document classification on a modern scale. InProceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining 2011 Aug 21 (pp. 231-239).
- Aggarwal C. Recommender Systems. Available from: https://pzs.dstu.dp.ua/DataMining/recom/bibl/1aggarwal_c_c_recommender_systems_the_textbo ok.pdf
- Kowsari K, Jafari Meimandi K, Heidarysafa M, Mendu S, Barnes L, Brown D. Text classification algorithms: A survey. Information. 2019 Apr;10(4):150.
- Guo J, Deng Y, Wang D, Meng H, Zhao Z. RadarDMath: Learning path recommendation system based on knowledge graph. InProceedings of the 2023 International Conference on Information Education and Artificial Intelligence 2023 Dec 22 (pp. 476-482).
Journal of Computer Technology & Applications
| Volume | 17 | |
| 02 | ||
| Received | 01/03/2026 | |
| Accepted | 14/04/2026 | |
| Published | 25/05/2026 | |
| Publication Time | 85 Days |