Fair and Transparent AI-Driven Resume Screening: Enhancing Recruitment with Bias-Aware Machine Learning

Abstract

The increasing volume of job applications has made resume screening a time-consuming and challenging task for recruiters. Traditional keyword-based filtering methods often fail to capture the true relevance of resumes to job descriptions, leading to inefficiencies and potential biases in candidate selection. To address these challenges, we propose an AI-driven Intelligent Resume Sorting System that leverages Natural Language Processing (NLP) and Machine Learning techniques for automated resume categorization. The system employs TF-IDF, BERT embeddings, and deep learning classifiers to extract and analyze key resume attributes, ensuring accurate classification based on job roles. Our model achieves 93% accuracy, significantly outperforming traditional screening methods while reducing processing time by over 50%. Additionally, by minimizing human intervention, our approach enhances fairness and mitigates biases in recruitment. This research contributes to the advancement of AI-driven hiring solutions, offering a scalable, efficient, and equitable method for modern talent acquisition.