AUTOMATED RESUME ANALYSIS AND SKILL SUGGESTING WEBSITE USING NLP

Abstract

The rapid growth of digital recruitment platforms has made manual resume screening timeconsuming and inefficient. This project proposes an intelligent web-based system for automated resume analysis and skill recommendation using Natural Language Processing (NLP) and machine learning techniques. Resumes in PDF and DOCX formats are converted into text and processed using tokenization, stop-word removal, normalization, stemming, and lemmatization. Named Entity Recognition (NER) extracts candidate information such as education, organizations, designations, skills, certifications, and projects. TF-IDF converts resume and job-description text into numerical representations, while Cosine Similarity measures their relevance. Based on similarity scores, the system identifies skill gaps, generates ATS compatibility scores, ranks candidates, and provides personalized skill recommendations. It can also suggest relevant online courses. The proposed system reduces recruitment effort, improves screening efficiency, supports candidate selection, and helps job seekers enhance their professional skills. Keywords: NLP, Resume Analysis, NER, TF-IDF, Cosine Similarity, Skill Gap Analysis, ATS, Recruitment Automation.