JOB RECOMMENDATION SYSTEM USING AI & ML

Abstract

The fast growth of digital recruitment platforms is changing the way we hire. These online tools make it easier for companies to connect with job seekers, streamlining the process and giving everyone involved new chances. made it hard to handle a lot of resumes. Manually screening candidates takes a lot of time and is easy to make mistakes. This study introduces an intelligent Job Description Matcher system that use Natural Language Processing and Deep Learning to automate recruitment procedures. Using PyPDF2, docx2txt, and Tesseract OCR, the system can read resumes in a number of formats, such as PDF, DOCX, and scanned documents. Named Entity Recognition models pull out structured information like skills, education, and work history. A hybrid similarity method that uses TF-IDF, Cosine Similarity, Jaccard Similarity, and BERT-based Sentence Transformers to look at both lexical and semantic factors to see how well an applicant fits a job. The system has a job recommendation module and a way to rank candidates. The platform was built with Flask and MongoDB and is better at matching candidates than traditional keyword-based systems. It also makes sure that candidate selection is fair and can grow with the needs of the business.