The ever-increasing complexities in the modern job market have created many challenges for students and job seekers in choosing the right career path, understanding the skills required, and preparing application documents according to the job requirements. Traditional career guidance methods involve a few isolated processes such as aptitude tests, resume building, or job listings. These methods do not offer a comprehensive and personalized career guidance system. In order to overcome the limitations and challenges associated with the traditional career guidance methods, the authors propose a new system named HCPRA (Hybrid Career Prediction and Resume Adaptation) using the power of Artificial Intelligence. This system will enable the user to undergo a series of career planning and job preparation processes. This proposed system will comprise four main functionalities such as career role prediction, skill gap prediction, resume building, and job suggestion. The system aims to evaluate academic, technical, and domain-specific profile attributes in order to predict potential career paths, detect skills gaps, and semantically match resumes with relevant job openings. In order to evaluate the effectiveness of the proposed system’s career prediction module, four machine learning algorithms have been implemented and compared: Logistic Regression, Random Forest, Gradient Boosting, and CatBoost. Among these algorithms, CatBoost has shown the best performance for the proposed framework.
p et al. (2026) studied this question.