The rapid growth in job applications across digital recruitment platforms has created significant challenges for organizations in efficiently identifying suitable candidates. Manual resume screening is time-consuming, error-prone, and susceptible to subjective bias. This paper presents an AI-driven Resume Screening and Job Matching System that automates candidate evaluation using Natural Language Processing (NLP), Machine Learning (ML), and semantic similarity techniques. The system extracts structured information from unformatted resumes, generates candidate profiles, and computes a relevance score by comparing skills, experience, and domain expertise against job requirements. A hybrid ranking model integrating rule-based filters with transformer-based embeddings (e.g., BERT or Sentence-BERT) ensures high-precision matching while minimizing false positives. Additional modules, including duplicate detection, candidate shortlisting, and recruiter dashboards, enhance end-to-end hiring efficiency. Experimental results demonstrate improved screening speed by up to 80% and significantly higher accuracy in candidate-job alignment compared to traditional keyword-based methods. This work highlights the potential of AI-enabled recruitment pipelines to support unbiased, scalable, and data-driven hiring decisions.
Building similarity graph...
Analyzing shared references across papers
Loading...
M Sivakumar
Mr. E. Rajamanickam
Building similarity graph...
Analyzing shared references across papers
Loading...
Sivakumar et al. (Fri,) studied this question.
www.synapsesocial.com/papers/6a0d4ee2f03e14405aa9a038 — DOI: https://doi.org/10.56975/jaafr.v4i5.509836