Author(s): Harshada Ishwar Borude

Abstract: The hiring process is undergoing a digital transformation as companies seek efficient methods to manage the growing volume of job applications. Traditional manual resume screening is labour-intensive, inconsistent, and often influenced by unconscious biases. This paper presents an AI-based resume screening system that leverages Natural Language Processing (NLP) and Machine Learning (ML) techniques to streamline recruitment. The system is designed to parse and analyze resumes, match them with job descriptions, and provide a ranked list of suitable candidates. The approach involves structured data extraction, semantic comparison using word embeddings, and scoring based on relevance, experience, and skill match. Training data is derived from historical recruitment records to build predictive models that improve over time. Unlike keyword-based filtering, this system understands context and semantics, enabling more accurate candidate evaluation. It also adapts through a feedback loop, incorporating recruiter preferences to enhance future recommendations. Implementing such AI-based systems not only speeds up the recruitment cycle but also reduces operational costs and improves hiring quality. The proposed system is particularly beneficial for large organizations and recruitment agencies handling high application volumes. Results from experimental validation demonstrate significant improvements in accuracy, efficiency, and fairness compared to traditional methods. Future enhancements may include video analysis for interviews and integration with applicant tracking systems. This paper outlines the system architecture, methodology, and practical applications, offering a transformative approach to talent acquisition in the era of artificial intelligence.

DOI: 10.33545/27076636.2025.v6.i2a.122

Pages: 133-136 | Views: 463 | Downloads: 313

Download Full Article: Click Here