Automated Resume Screening System Using NLP and Machine Learning

Abstract

Abstract—Modern recruitment struggles with the inefficiencies of manual resume screening, a process often slow, error-prone, and biased. We present an AI-powered system that integrates natural language processing (NLP) and machine learning (ML) with a MERN stack platform to automate resume extraction, analysis, and ranking. Using a dataset of resumes from diverse sources, we employed advanced NLP techniques—such as named entity recognition—and ML models like logistic regression and random forests to rank candidates efficiently. Integrated with a scalable MERN stack, the system offers recruiters a user-friendly portal with ranked candidate lists and insightful visualizations. Testing on a 300-resume sample achieved 95% accuracy, while processing 500 resumes took just 15 minutes. This solution reduces errors, mitigates bias, and accelerates hiring, offering a practical, innovative tool for HR teams. Key Words—resume screening, natural language processing, machine learning, MERN stack, recruitment automation