An Automated NLP Framework for Resume Screening and Ranking Using TF-IDF and Rule-Based Matching

Organizations get a large number of resumes for each job opening, and they employ resume or archive screeners to select the competent and exceptional applicants. However, resume screening is an important and time-consuming element of the decision-making process. While screening resumes, there are various factors to examine, such as the candidate’s abilities, job experience, designation, and degree. To the degree that business is reviewed, selecting the best candidate for the enrollment cycle from a large pool of candidates has been a significant challenge. As a decision-making tool, this research work assists the screeners in effectively shortlisting the resumes. This system mines resume striking highlights of applicant profiles like personal details, skills, experience in every expertise, training subtleties, and past experience by utilizing Natural Language Processing (NLP). The proposed system gives a specialized labor force to the association, which will assist any department by selecting the correct candidate for the specific occupation profile. The proposed project works on a dynamic format of resumes. The competitor resumes are then contrasted with the expected set of responsibilities posted by the organization or the enrollment specialists by utilizing wise strategies. Scores would then be given to the resumes, and they can be positioned in a descending order. This positioning is made available exclusively to the company or recruiter on their portal to assist them in selecting the best candidate from a large pool of up-and-comers.