| Abstract |
Students at different stages of their educational journeys face the difficult task of selecting from a wide range of academic and professional opportunities in today's dynamic world. According to reports, young people, especially those in the OECD countries, have greater unemployment rates than adults over the age of 25 (Musset, P., & Kureková, L., n.d.). This emphasizes how urgently early-career decision-makers need nuanced guidance.
Our team has developed a customized recommendation system that is tailored to the unique profiles of IT and engineering students. The system offers focused recommendations for improving career paths. It is based on data extracted from platforms such as Coursera and LinkedIn and student academic records. Our method starts by gathering the necessary data such as user input and students' grades from IT classes and storing it in the MongoDB database, by utilizing machine learning algorithms to process and predict CGPA results. The “NAHJ” system provides personalized recommendations based on these forecasts, such as extra courses for students in need of academic help, career, and postgraduate opportunities for top achievers.
The system presents these recommendations in an engaging and easily navigable user streamlit interface. The model is dynamic and grows with the student because of ongoing adaptation to user feedback. This project makes a substantial contribution to students' readiness for the workforce and skill development. We show that meeting the specific needs of students moving from educational institutions into the workforce requires not only a feasible but also an innovative, data driven approach.
|
