Resume Screening using Machine Learning

Abstract

Abstract–The rapid advancement of the technology field has ushered in a wave of employment opportunities across various sectors, necessitating organizations to efficiently sift through a multitude of resumes to identify the most suitable candidates for their specific job requirements. To address this challenge, we propose a research paper that presents a systematic approach to effectively sorting resumes based on company-specific requirements, enabling the identification of the most qualified candidates for specific job roles. This research paper introduces a cutting-edge solution that harnesses state-of-the-art technologies, including Machine Learning and Natural Language Processing (NLP), in conjunction with cosine similarity. A model has been developed to recognize keywords and extract pertinent information from job requirements provided by recruiting companies. To train this model, a comprehensive database of diverse resumes from various fields has been employed. The model is trained to exclusively search for keywords or requirements specified by the recruiting company, thereby sorting the resumes, accordingly, accepting those that align with the specified criteria, and dismissing those that fall short. The entire process is designed to optimize efficiency and streamline the candidate selection process. Keywords: Natural language processing, Cosine Similarity, Tfidfvectorizer.