Abstract:
"This research examines the implementation of Resume filtering software
to address the issue of effectively evaluating a job applicant's shown performance based
only on the information stated on their Resume. Resume filtering tools have become rapidly
important in today's job market due to the massive number of resumes received for each
job position. Such tools assist in automating the screening process by filtering out
irrelevant or unqualified candidates as per the criteria estimated by the recruiter. The
widespread practice of candidates intentionally hiding information in their Resumes has
affected Resume filtering software in order to separate candidates with actual essential
qualities from candidates who use fraudulent methods to divert the software tool. Such
activities have become a challenge for recruiters to accurately assess applicants'
qualifications and work experience. The proposed desktop application is designed to
detect fraudulent activities and filter candidates based on their work experience.
Machine learning (ML) and optical character recognition (OCR) are the major
technologies utilized in the proposed Resume filtering tool. Due to the involvement of
uncertainty in requirements and continuous feedback from the general users and
industry experts, the most productive way of software development methodology is the
hybrid approach of combining Agile and Waterfall methodologies. Furthermore, the
proposed system not only saves time and resources in hiring the process but also ensures
a fair and objective evaluation of all applicants."
