Augmented Intelligence Approach To Educational Data Mining: Student Drop Prediction

Educational Data Mining (EDM) and Augmented Intelligence (AUI) are two upcoming fields in the machine learning research industry. EDM refers to the use of machine learning elements in an educational format. Typically, this is in the form of utilizing educational data to better understand the learning process. Augmented Intelligence, on the other hand, is a niche of machine learning that refers to people taking a much larger role than typical in artificial intelligence projects. For example, a professional in a given field may provide better insight as to what metrics should be weighed more when considering a given prediction. In this thesis, I review the feasibility of using Augmented Intelligence in the genre of Educational Data Mining to predict the likelihood of a student dropping a course based on demographic, study habit, and student perception information recorded through a survey. Additionally, I will be testing three optimization algorithms to see which is most beneficial in the application of this research. The goal of this research is to ultimately provide instructors with a machine learning model capable of highlighting at risk students such that the instructor can provide intervention techniques in a more timely fashion.