Comparative Analysis of Job Recommendation Filtering Techniques

The objective of the paper is to present a technical and novel comparative study of job recommendation filtering techniques, addressing gaps in existing research. We evaluate Content-Based (CBF), Collaborative Filtering (CF), and Hybrid models, introducing a Graph-Enhanced Hybrid Model that improves skill-aware recommendations using Graph Neural Networks (GNNs). Our evaluation includes accuracy, diversity, novelty, and fairness metrics, demonstrating superior performance over baselines.