Resume Screening Automation: Enhancing Recruitment Efficiency with Machine Learning Algorithms

Abstract

 Resume screening is an important step in recruitment, but it is also one of the most time-consuming activities, as well as ineffective and discriminatory in traditional techniques. Manual screening and basic keyword-matching methods are more harmful than beneficial, because their results create an incomplete image of prospects and may ignore the most eligible people. The study reported in the paper provides an automated resume screening system that improves applicant selection by leveraging machine learning (ML) and natural language processing (NLP). By pushing beyond algorithms and keyword-based techniques,   the proposed system can interpret contextual information in resumes and job descriptions. Using classifiers like as Random Forest (RF) and Support Vector Machines (SVM), the system gradually improves its predictions as it learns from hiring data. Experimental results show that, when compared to conventional methods, the proposed system achieves 88.3% accuracy, 90.1% precision, and 86.7% recall. It addresses the data imbalance issue by reducing false positives and negatives and making the recruitment process fair, efficient, and scalable.