Data mining for modelling students' performance by analysing activity grades temporal data: A tutoring action plan to prevent academic dropout

Abstract

E-learning systems generate huge amounts of data, whose analysis may become a daunting task which makes it necessary to use computational analytical techniques and tools.

We propose the use of knowledge discovery techniques to analyse historical student course grade data in order to predict whether or not a student will drop out of a course. Logistic regression models are used for the purpose of classification. Experiments conducted with data on over 100 students for several distance learning courses confirm the predictive power of our proposal. Using the resulting predictive models we have designed a tutoring action plan. Applying this plan, we managed to reduce the dropout rate by 14% with respect to previous academic years in which no dropout prevention mechanism was applied.

Our main contribution is a tool and a tutoring plan that can be used by our educational institution (and others) to reduce dropout rate in e-learning courses.