Predicting Student Performance through Bloom's Taxonomy using Data Mining Framework for Educational Decision Making

Abstract

Predicting student performance is an invaluable undertaking within the domain of educational decision-making. A novel methodology is presented in this study, which combines sophisticated data mining techniques with Bloom's Taxonomy, a widely recognised educational framework. The study seeks to improve the precision and comprehensiveness of predictive models pertaining to student performance through the utilisation of this fusion.By providing a structured hierarchy of cognitive processes, Bloom's Taxonomy enables educators to gain a more comprehensive comprehension of the learning outcomes of their students. By implementing data mining techniques, including classification and clustering algorithms, this framework empowers instructors to derive significant insights from a wide range of student datasets. These observations not only facilitate the forecasting of individual student achievement but also provide guidance for the design of instructional approaches and curricula. The framework that has been proposed signifies a substantial progression in the realm of educational decision-making. It offers instructors a potent instrument to enhance learning experiences and promote scholastic achievement.