PERSONALIZED CAREER PATHWAY: A HYBRID MACHINE LEARNING APPROACH FOR DYNAMIC RECOMMENDATIONS

Abstract

This paper presents a conceptual framework for a hybrid machine learning-driven career pathway recommendation system designed to provide personalized, dynamic and real-time job transition insights. The proposed system leverages skill-centric approaches using content-based and collaborative filtering to match users with relevant job opportunities and suggest targeted upskilling pathways. Real-time adaptability is integrated to ensure that the recommendations remain current, reflecting changes in user profiles and market demands. Furthermore, temporal analysis is employed to predict career progression patterns, enabling users to make informed decisions about future transitions and milestones. By combining these approaches, the framework aims to offer a comprehensive solution for personalized career guidance, addressing key challenges such as data sparsity, real-time updates and evolving career trajectories. This paper outlines the design and potential applications of the framework while discussing the benefits, challenges and future research directions.