Published Paper Details:

Manual resume screening is one of the most resource-intensive stages of recruitment, often consuming excessive time and introducing unconscious biases into hiring decisions. With the exponential rise of digital job portals, recruiters face overwhelming applicant volumes, making traditional keyword-based filtering insufficient. This paper proposes an AI-powered resume screening framework that integrates Natural Language Processing (NLP), predictive analytics, and optional video resume evaluation to improve both efficiency and fairness in candidate selection. The proposed model extracts structured information from unstructured resumes, matches candidates with job requirements using similarity measures, and applies predictive models to forecast retention likelihood. An ethical layer ensures de-biasing, anonymization, and compliance with legal safeguards. A synthesis of prior research demonstrates that AI-driven systems can reduce screening time by up to 60%, improve candidate-job matching compared to keyword search, and enhance engagement when video resumes are included, though legal concerns remain,The findings highlight that AI-powered screening can significantly transform HR practices while requiring careful attention to bias and privacy challenges.