AI-BASED RESUME SCREENING AND JOB RECOMMENDATION FRAMEWORK

Abstract

The rapid growth of online recruitment platforms has led to an overwhelming volume of resumes submitted for every open position, making manual screening slow, inconsistent, and prone to human bias. This paper presents an AI-Based Resume Screening and Job Recommendation Framework that automates candidate evaluation and job matching using Natural Language Processing (NLP) and Machine Learning (ML). The framework extracts structured information from unstructured resumes, converts resumes and job descriptions into semantic vector representations, and computes similarity scores to rank candidates against job requirements. A complementary recommendation module suggests suitable job postings to candidates based on skills, experience, and career trajectory. Evaluation on a curated dataset shows that the framework achieves higher precision, recall, and ranking accuracy than traditional keyword-matching Applicant Tracking Systems (ATS), while substantially reducing manual screening time