Optimizing Job Matching Through Automated Resume Screening with NLP and Machine Learning

Resume screening determines a candidate's qual-ification for a position based on their education, experience, and other resume information. Candidates are only called for interviews if their resume matches the job description. Manual resume examination is time-consuming and burdensome, prompting companies to use applicant tracking systems to shortlist candidates based on their skills. The primary cause of rejection is often a mismatch between the job role and the applicant's skill set. Job seekers must understand which job categories align with their skill sets. This study employs natural language processing (NLP) and machine learning (ML) techniques to evaluate applicants in real time. Methods such as tokenization, stemming, lemmatization, TF-IDF, and string matching are used to identify keywords. Subsequently, ML models are applied to determine the most suitable role for each applicant. Four models-SVM, logistic regression, random forest, and k-nearest neighbors-are compared for accurate classification, with SVM outperforming the other benchmarks. This project aims to revolutionize the resume screening process by integrating advanced technologies and refining our methodologies.