A Predictive Analytics System for Forecasting Student Academic Performance: Insights from a Pilot Project at Eastern Washington University

摘要

Our work is focused on determining whether any correlation exists between preparatory classes taken by Electrical Engineering (EE) students at Eastern Washington University (EWU) early in their academic careers (e.g. Calculus and Physics sequences) and their departmental GPAs upon graduation. Using academic data from prior EE graduates, a machine learning algorithm was trained to predict with 85% certainty whether a student's GPA will fall above/below one standard deviation from the mean. This prediction can be used to channel university resources to support those students who need it the most. However, there is a significant prediction overlap for average students, i.e. those who fall within approximately one standard deviation around the mean. It is our conjecture that incorporating more major-specific data (e.g. grades in a set of core introductory level departmental courses) or a customized general aptitude test administered at the end of the sophomore year could improve the prediction accuracy for the average group.