Predicting STEM academic performance in secondary schools: data mining approach

STEM is a curriculum based on the idea of educating students in four specific disciplines — science, technology, engineering and mathematics — in an interdisciplinary and applied approach. Skills developed in students through STEM provide them with strong foundation to succeed in school and beyond. STEM is expected to increase students’ critical thinking skills which very much needed in the workforce especially to support for the growth of the economy during the industrial revolution. The main objective of this study is to investigate the appropriateness of applying data mining approach to predict and analyze STEM academic performance in secondary schools. In this study, data will be collected randomly from schools all over Malaysia. There are two types of data collected namely primary and secondary data. Primary data will be collected through questionnaire whereas secondary data will be collected from the schools or information through the internet. Three different data mining classification algorithms which are Decision Tree (DT), Artificial Neural Networks (ANN), and Naive Bayes (NB) will be used on the dataset. This study is expected to investigate the process through utilize classification to help to predict students’ performance. As a result of this insight, it will gives useful insight of explicit and tacit knowledge to students, teachers, parents and minestry in predicting student performance in STEM and to assist teachers in providing effective teaching method