AN AUTOMATED RESUME SCREENING SYSTEM USING NATURAL LANGUAGE PROCESSING AND SIMILARITY
Chirag Daryani, Gurneet Singh Chhabra, Harsh Patel, Indrajeet Kaur Chhabra, Ruchi Patel
Abstract
A typical job posting on the Internet receives a massive number of applications within a short window of time. Manually filtering out the resumes is not practically possible as it takes a lot of time and incurs huge costs that the hiring companies cannot afford to bear. In addition, this process of screening resumes is not fair as many suitable profiles don't get enough consideration which they deserve. This may result in missing out on the right candidates or selection of unsuitable applicants for the job. In this paper, we describe a solution that aims to solve these issues by automatically suggesting the most appropriate candidates according to the given job description. Our system uses Natural Language Processing to extract relevant information like skills, education, experience, etc. from the unstructured resumes and hence creates a summarised form of each application. With all the irrelevant information removed, the task of screening is simplified and recruiters are able to better analyse each resume in less time. After this text mining process is completed, the proposed solution employs a vectorisation model and uses cosine similarity to match each resume with the job description. The calculated ranking scores can then be utilised to determine best-fitting candidates for that particular job opening.