RESUME SCREENING USING TF-IDF

Abstract: The goal of resume screening is to find the best candidates for a position. In order to match and rate candidates in real-time, the software must employ natural language processing and machine learning. Our system is a resume ranking software that uses natural language processing (NLP) and machine learning. Input would be resumes and job descriptions, output would be a highly ranked candidate’s resume. Output results are acquired instantly in real-time. We will be using Mong for string matching, Cosine Similarity, TF-IDF. The existing systems are simple and effective but are not robust in terms of accuracy, efficiency, and processing. Through the analysis of the works of literature on existing methods, it can be found that these are traditional systems that could lead to inaccurate assumptions and loss of human potential. We propose a web application that aims to order the resumes, by intelligently reading job descriptions as input and comparing the resumes which fall into the category of given Job Descriptions. In order to match and rate candidates in real-time, the software employs natural language processing It provides a ranking after filtering and recommends the better resume for a given textual job description. The Advantages of the proposed system are Secured, Interpretability, High accuracy, Lightweight model & fast processing. Real-time use cases. It could be used in MNC’s where multiple resumes must be screened every single day for multiple jobs, government, and administrative offices.