Resume Ranking Engine Using Machine Learning and Natural Language Processing for Automated Candidate Screening

Organizations often receive hundreds of resumes for a single job opening, making manual candidate screening slow and difficult to manage. Conventional recruitment methods generally depend on keyword matching or manual evaluation, both of which may overlook qualified applicants because of differences in resume structure and terminology. This research presents a Resume Ranking Engine that automates candidate screening using Machine Learning (ML) and Natural Language Processing (NLP). The proposed application extracts candidate information from PDF and DOCX resumes, preprocesses the extracted text, and compares it with a job description using TF-IDF vectorization and cosine similarity. In addition to textual relevance, the system evaluates technical skills, educational qualifications, and professional experience through a weighted scoring strategy. The application is implemented using React, Flask, Python, and Supabase, providing recruiters with a simple interface for uploading resumes and obtaining ranked candidate lists. The proposed approach reduces manual effort, improves consistency during recruitment, and provides an effective decision-support tool for candidate shortlisting.