Automated Resume Parsing using Name Entity Recognition

Abstract - The traditional hiring process often involves manually reviewing numerous resumes, making recruitment time-consuming and costly. To address this challenge, we propose an Automated Resume Parsing System using Named Entity Recognition (NER), an advanced Natural Language Processing (NLP) technique. Our system efficiently extracts key information, such as candidate names, skills, education, and work experience, from unstructured resume data, enabling structured representation and faster decision-making. By automating resume screening, our approach significantly reduces hiring costs and minimizes recruiter workload while improving accuracy in candidate selection. Furthermore, it enhances the efficiency of applicant shortlisting by filtering out irrelevant job applications. The system leverages machine learning models trained on diverse resume datasets to improve extraction accuracy and adaptability to various resume formats. Additionally, it integrates with applicant tracking systems (ATS) for seamless recruitment workflow automation. Experimental results demonstrate that our system achieves high precision in entity recognition, making it a valuable tool for modern recruitment platforms. The proposed solution not only optimizes the hiring process but also contributes to fair and unbiased candidate evaluation. Key Words: Automated Resume Parsing, Named Entity Recognition, Natural Language Processing, Recruitment Automation, Applicant Tracking System, Resume Screening, Machine Learning