Resume Parsing and Ranking System For LinkedIn using NLP

In today's competitive job market, efficiently identifying the most suitable candidates " "among a vast pool of applicants is crucial for organizations. This project presents a Hybrid " "Resume Parsing and Ranking System that leverages advanced Natural Language Processing (NLP) techniques, " "deep learning, and transformer models to streamline the candidate selection process. The system extracts " "key information from resumes using rule-based methods and Named Entity Recognition (NER) powered by SpaCy's " "pre-trained models. It ranks resumes using cosine similarity between the extracted information and job " "descriptions, with vectorization done through Sentence-BERT (SBERT). Implemented using Python, with libraries " "like SpaCy, Regex, and PyTorch, the system enhances recruitment efficiency by saving time and resources while " "ensuring relevant resumes are prioritized.