Every single day, businesses and organizations receive too many resumes to feasibly go through manually. Standard Applicant Tracking Systems (ATS) primarily work by matching keywords; therefore, there are many qualified applicants that will sometimes not appear in an ATS because they described their experiences with words that were not searched upon. In addition to the applicant’s language being different than what was searched for, resumes are typically formatted differently, which makes the task of comparing resumes even more difficult than it already is. The intelligent resume parsing and skills analytic system that we propose will utilize Natural Language Processing (NLP) to provide a solution to many of the ATS’ problems in regards to matching resumes to jobs. When any PDF resume is submitted to the intelligent resume parsing system, there will be a multi-stage process to extracting information from the resume: The first stage will extract the text from the PDF file, then format the text, identify important entities (e.g. Name and contact information), and finally retrieve all relevant technical skills. The final stage involves scoring each applicant’s experience/education relative to the job description using TF-IDF vectorization through cosine similarity, which produces a score that can be easily compared between applicants. All information will be stored in a SQLite database and recruiters will interact with this information through a Streamlit web interface which provides visualizations, metrics, and side-by-side comparisons of applicants.In testing, the intelligent resume parsing system was able to extract 92.1% of the entities included in 500 resumes from various technology fields; classify technical skills with 89.4% accuracy; and provide approximately 90.2% resume-to-job matching accuracy. These testing results confirm that the combination of utilizing NLP, scoring based upon similarity to job descriptions and recruiter interaction through visualization are effective in gathering accurate information for applicants and generating an accurate comparison between two or more applicants.
Resume Parsing; Natural Language Processing; Named Entity Recognition; TF-IDF; Cosine Similarity; Skill Analytics; Streamlit; SQLite
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.