Data Mining Approach for Early Student Performance Prediction Using Machine Learning: Process Control and Mechanism ^†

Context: Our research activities aim to bridge the gap between traditional process/system-related fields and the innovative application of process systems engineering principles in education through the lens of data mining. By leveraging machine learning techniques, particularly in early student performance prediction, we aim to showcase the relevance and potential of process control and mechanisms in optimizing educational systems. Specifically, our study demonstrates how concepts such as feature selection, model evaluation, and performance metrics, commonly used in process systems engineering, can be applied to educational data mining. Objective: Our objective is to demonstrate the significance and possibilities of process management and mechanisms in enhancing educational systems through the utilization of machine learning techniques, specifically in the early student performance prediction domain. We focus on early student performance prediction using machine learning and aim to show how ideas from process systems engineering, such as feature selection, model assessment, and performance metrics, may be effectively applied in educational data mining. Material/Methods: Using a data mining technique, our research presents a cross-disciplinary examination of the use of process control and mechanisms in education. Our work emphasizes the applicability of process systems engineering principles across several domains, such as chemistry, biology, materials science, energy, environmental science, food technology, and engineering. Our extensive dataset includes student performance scores over several semesters. Through meticulous feature selection and rigorous evaluation methods, we obtained promising results, including an accuracy of 99% and an R-squared value of 1.00. Conclusion: Our interdisciplinary approach offers valuable insights into the current state, challenges, and opportunities within both educational research and process systems engineering. By showcasing the cross-disciplinary implications of our work, we aim to contribute to the advancement of process systems' engineering principles in diverse domains, including education.