RESUME SHORTLISTING AND RANKING WITH TRANSFORM

Abstract

The recruitment process often involves reviewing a large number of resumes, which is time-consuming and prone to human bias. This project proposes an automated resume shortlisting and ranking system using Transformer-based deep learning models, such as BERT, to efficiently evaluate candidate resumes. The system extracts relevant features from resumes, including skills, education, experience, and certifications, and matches them against job descriptions to assess suitability. By leveraging contextual embeddings and semantic analysis, the Transformer model can understand the nuances in candidate profiles and provide an accurate ranking. Experimental results demonstrate that this approach reduces manual effort, minimizes bias, and improves the efficiency and fairness of candidate selection. The system can be applied in various human resource management platforms to streamline recruitment and enhance decision-making