An Integrated Deep Learning Framework for Personalized Career Guidance and Course Recommendation

Abstract

The transition from academia to a professional career is a critical phase for students, often marked by uncertainty in selecting an appropriate job role. This uncertainty is compounded by a lack of awareness of the requisite skills and the vast array of available learning resources. Many organizations and corporate entities offer high-quality, free courses on platforms like NPTEL, Coursera, edX, Microsoft Learn, and Google Learning, yet students frequently remain unaware of these opportunities. This paper proposes an integrated system designed to mitigate these challenges. The system employs a Deep Neural Network (DNN) model to predict suitable Information Technology (IT) job roles for students based on their academic profiles, skills, and interests, achieving a prediction accuracy of 90.87%. Subsequently, a content-based course recommendation engine suggests relevant, free courses tailored to the predicted job role, leveraging cosine similarity for optimal matching. By consolidating courses from numerous free platforms into a single dataset, the system provides a centralized hub for skill development. This approach not only offers personalized career guidance but also facilitates access to valuable educational content, thereby bridging the gap between academic knowledge and industry requirements and empowering students to make informed career decisions.