AI-Powered Resume Ranker System

Abstract

The rapid growth of online recruitment platforms has significantly increased the volume of job applications received by organizations. Traditional Applicant Tracking Systems (ATS) rely heavily on keyword-based filtering and manual screening, which are often time-consuming, inconsistent, and prone to bias. This paper presents an AI-Powered Resume Ranker System that leverages Natural Language Processing (NLP), semantic embeddings, and machine learning techniques to automate candidate evaluation and ranking. The proposed system extracts structured information from resumes, generates contextual embeddings using transformer-based models, and computes similarity scores between resumes and job descriptions. Experimental results demonstrate improved accuracy (88%) compared to traditional ATS systems (55%). Performance evaluation using ROC curves (AUC = 0.90), confusion matrix analysis, and similarity convergence graphs confirms the robustness of the proposed framework. The system reduces recruitment time, enhances fairness, and improves hiring quality.