Automated Resume Parsing and Ranking using Natural Language Processing
K. Thangaramya, G Logeswari, Sudhakaran Gajendran, J. Deepika Roselind, Neha Ahirwar
Abstract
Advancements in networking and communication have revolutionized the recruitment process, leading to the development of modern resume parsing and ranking systems. With the proliferation of internet-based recruiting, numerous resumes are now stored in recruitment systems. However, traditional methods, such as manual processing and the utilization of unique resume templates, have limitations when dealing with unstructured documents like resumes. Resume parsing is a crucial technique that involves extracting essential details pertaining to applicants to be shortlisted for interview. This paper introduces the “Resume Parser and Ranker,” an application designed to efficiently and automatically rank resumes, saving considerable time and manpower during the recruitment process. The application is powered by Natural Language Processing (NLP) approach, incorporates heuristic calculations to evaluate the final score of each candidate. The system utilizes Deep Learning (DL) for Named Entity Recognition (NER), achieving an impressive 93% accuracy in information extraction. Notably, this accuracy is close to the level achieved by humans, which typically does not exceed 96%. The high accuracy of the resume parser ensures reliable results, enabling companies to identify the most suitable candidates who can be called for further interview rounds.