AI Driven Career Path Recommendation System

Abstract

Traditional job search platforms often fail to provide personalized recommendations, leading to inefficiencies in the hiring process. This paper presents an AI-powered job recommendation system using a recurrent neural network (RNN) with a two-layer attention mechanism. The proposed system improves job-candidate matching by leveraging multi-source data, including user behavior, recruiter preferences, and job descriptions. By employing the TransR method for entity representation, the model enhances search accuracy and job relevance. The experimental results demonstrate that the proposed system significantly outperforms traditional methods in recommendation precision and recall.