Understanding trends in higher education student performance using machine learning techniques

Several factors contribute to the success of any student. Apart from the educative curriculum, differentiators like family background, wealth, time commitment, and involvement can be used to predict the grade outcomes of a student. This analysis provides early help to students who lack in certain areas by addressing such issues. A dataset populated by data from 145 students helps us assess factors that could affect a student's performance. Using binary and ternary classification on the dependant variable, we try to target students which need academic attention. We apply multiple structured machine learning algorithms to analyze and compare different models.