The rapid growth of online recruitment platforms has increased the number of job applications received by organizations, making manual resume screening time-consuming and inefficient. Traditional recruitment methods often rely on keyword matching and manual evaluation, which may lead to inaccurate candidate selection and human bias. This research proposes an AI-Based Applicant Tracking System (ATS) for Resume Analysis and Skill Gap Prediction using Natural Language Processing (NLP) techniques. The system uses TF-IDF vectorization and cosine similarity algorithms to compare resumes with job descriptions and calculate candidate compatibility scores. A skill gap prediction module identifies missing skills required for specific job roles. The proposed system also includes a dashboard analytics module that displays recruitment metrics such as total resumes analyzed, highest match score, average compatibility score, and candidate ranking. In addition, the HOT-Fit model is used to evaluate the system from human, organizational, and technological perspectives. The proposed framework improves recruitment efficiency, reduces manual effort, supports transparent hiring decisions, and enhances candidate-job matching accuracy through AI-driven analysis.
Raghavendra et al. (Tue,) studied this question.