Paper Title
AN AI-BASED RECOMMENDATION SYSTEM FOR FORMATIVE ASSESSMENT TOOLS IN ENGINEERING EDUCATION

Abstract
Formative assessment (FA) plays a crucial role in student learning and performance evaluation. However, selecting an appropriate FA tool that effectively supports learning for all students remains challenging. In many cases, certain FA tools do not contribute meaningfully to learning but are still administered for grading purposes. To address this issue, we propose a smart FA recommendation system leveraging machine learning to personalize assessment strategies for each student. The system collects student-specific inputs such as study hours, learning style, preferred FA tools, and Bloom’s taxonomy levels (remembering, understanding, apply-ing, analyzing, evaluating, and creating). Based on these data, the machine learning algorithm recommends the most suitable FA tool for each student. Teachers can access the system to view recommended tools, analyze insights through simple visualizations, and finalize the most effective FA tool for the class. By implementing this system, students receive personalized formative assessments aligned with their learning preferences, while teachers can make informed decisions efficiently, reducing time and confusion in the assessment process. The approach enhances learning outcomes and supports a more targeted and effective assessment strategy.