Job Recommendation Systems Through AI and Machine Learning
Year: 2025
Type: article
Abstract: The explosive rise in digital recruitment platforms has generated the demand for smart systems that can make effective, personalized job recommendations. This paper introduces a new hybrid AI-driven job recommendation architecture that combines deep learning models (e.g., BERT for resume/job description embedding) with knowledge graph reasoning (to incorporate domain-specific semantics and relations) and reinforcement learning (for ongoing personalization). The system is tested against real-world job market data sets (e.g., Kaggle data set, Indeed, LinkedIn samples) and compared to baseline collaborative and content-based filtering methods. The outcomes show remarkable enhancements in recall, precision, and user satisfaction, which speak to the merits of fusing semantic comprehension with adaptive learning..
DOI: 10.14419/pr5w2v12
Authors: Sachin Soni, Sanjay Shah
Institution: Kadi Sarva Vishwavidyalaya
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4414353231