AI-Driven Resume Screening and Job Recommendation System

Abstract

We propose an AI-driven resume screening and job recommendation system designed to improve efficiency and accuracy in modern hiring processes. The system integrates two key components: a resume screening module that extracts and evaluates candidate features using a fine-tuned BERT model, and a job recommendation engine that combines similarity matching with predictive analytics. The resume screening component processes textual data to generate feature vectors, which are then compared against job requirements using cosine similarity for candidate ranking. Furthermore, the job recommendation component employs a hybrid scoring mechanism, blending similarity scores with predictive probabilities from a Gradient Boosting Machine to suggest suitable roles. The proposed method addresses critical challenges in recruitment, such as scalability and bias reduction, by automating feature extraction and decision-making. Our approach demonstrates significant potential to streamline hiring workflows while maintaining high accuracy, as evidenced by preliminary experiments. The system’s modular design allows seamless integration into existing recruitment platforms, offering practical value for both employers and job seekers. Moreover, the combination of transformer-based NLP and ensemble learning ensures robustness across diverse datasets and job domains. This work contributes to the growing body of research on AI-assisted hiring by introducing a unified framework that balances interpretability and performance. The results highlight the system’s ability to enhance candidate-job matching, thereby reducing manual effort and improving overall hiring outcomes.