An automated machine learning approach for early identification of at-risk maritime students
Open Access
Article
Conference Proceedings
Authors: Hasan Mahbub Tusher, Ziaul Haque Munim, Sajid Hussain, Salman Nazir
Abstract: Machine Learning (ML) presents a significant opportunity for the field of education, including Maritime Education and Training (MET). Unfortunately, the benefits of ML have yet to be fully realized within MET. By integrating ML and Artificial Intelligence (AI)-powered methods into maritime education, institutions can better prepare future seafarers while providing accurate, state-of-the-art education tailored to individual student needs. Early identification of areas for improvement can help students and teachers enhance educational outcomes within MET. This study showcases the potential of automated ML (AutoML) platforms for predicting future performance as well as for identifying at-risk maritime students at the initial stages of their degree program. By enabling early identification, institutions can more efficiently plan and execute education strategies while building confidence in AutoML as a decision-aid among maritime stakeholders.
Keywords: automated machine learning, artificial intelligence, maritime, education, training
DOI: 10.54941/ahfe1003150
Cite this paper:
Downloads
178
Visits
529