Early Detection of Students at Risk – Predicting Student Dropouts Using Administrative Student Data and Machine Learning Methods

41 Pages Posted: 31 Oct 2018

See all articles by Johannes Berens

Johannes Berens

University of Wuppertal

Kerstin Schneider

University of Wuppertal

Simon Görtz

University of Wuppertal

Simon Oster

University of Wuppertal

Julian Burghoff

University of Wuppertal

Date Written: 2018

Abstract

To successfully reduce student attrition, it is imperative to understand what the underlying determinants of attrition are and which students are at risk of dropping out. We develop an early detection system (EDS) using administrative student data from a state and a private university to predict student success as a basis for a targeted intervention. The EDS uses regression analysis, neural networks, decision trees, and the AdaBoost algorithm to identify student characteristics which distinguish potential dropouts from graduates. Prediction accuracy at the end of the first semester is 79% for the state university and 85% for the private university of applied sciences. After the fourth semester, the accuracy improves to 90% for the state university and 95% for the private university of applied sciences.

Keywords: student attrition, machine learning, administrative student data, AdaBoost

JEL Classification: I230, H420, C450

Suggested Citation

Berens, Johannes and Schneider, Kerstin and Görtz, Simon and Oster, Simon and Burghoff, Julian, Early Detection of Students at Risk – Predicting Student Dropouts Using Administrative Student Data and Machine Learning Methods (2018). CESifo Working Paper No. 7259, Available at SSRN: https://ssrn.com/abstract=3275433 or http://dx.doi.org/10.2139/ssrn.3275433

Johannes Berens (Contact Author)

University of Wuppertal ( email )

Gaußstraße 20
42097 Wuppertal
Germany

Kerstin Schneider

University of Wuppertal ( email )

Gaußstraße 20
42097 Wuppertal
Germany

Simon Görtz

University of Wuppertal ( email )

Gaußstraße 20
42097 Wuppertal
Germany

Simon Oster

University of Wuppertal ( email )

Gaußstraße 20
42097 Wuppertal
Germany

Julian Burghoff

University of Wuppertal ( email )

Gaußstraße 20
42097 Wuppertal
Germany

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
1,120
Abstract Views
3,106
Rank
35,739
PlumX Metrics