AI-POWERED RESUME SCREENING AND FEEDBACK SYSTEM

In the modern job market, the recruitment process is often hindered by the time-consuming and subjective nature of manual resume screening. Recruiters are faced with the challenge of evaluating thousands of applications efficiently while minimizing human error and bias. This project introduces a Smart Resume Screening and Evaluation System designed to automate and optimize the candidate evaluation process using Natural Language Processing (NLP) and Machine Learning (ML) techniques. The system accepts resumes in PDF format or as direct text input and utilizes text extraction methods to retrieve relevant information. It then compares the extracted content against predefined job descriptions using Count Vectorizer and Cosine Similarity to compute a matching score, which objectively indicates the alignment between a candidate’s qualifications and the job requirements. The platform also provides automated feedback for resume improvements and presents results using visualizations such as bar charts for enhanced interpretability. Developed with Streamlit for an interactive web interface and built on Python, the system employs PyMuPDF for text extraction, scikit-learn for similarity computations, and Matplotlib for graphical representations. Running on a Windows 11 environment, this AI-powered tool aims to streamline recruitment by increasing efficiency, reducing bias, and enabling data-driven decision-making. The proposed solution offers a standardized and scalable framework for resume screening. Future advancements may include semantic analysis, Applicant Tracking System (ATS) integration, and AI-based candidate recommendations. Ultimately, this system represents a step toward a fairer and more intelligent hiring process, benefiting both recruiters and job seekers.