Early prediction of university dropouts - a random forest approach

Behr, Andreas (University of Duisburg-Essen); Giese, Marco (University of Duisburg-Essen); Teguim Kamdjou, Herve Donald (University of Duisburg-Essen); Theune, Katja (University of Duisburg-Essen)
We predict university dropout using random forests based on conditional inference trees and on a broad German data set covering a wide range of aspects of student life and study courses. We model the dropout decision as a binary classification (graduate or dropout) and focus on...
published 2019, Version 1
Download

Full Metadata Record

Language of Resource

English

Title

Early prediction of university dropouts - a random forest approach

Creators

Behr, Andreas
Giese, Marco
Teguim Kamdjou, Herve Donald
Theune, Katja

Origin Information

Publisher

Publication Date

2019

Access

Availability

Download

Rights

Creative Commons Attribution 4.0 (CC-BY)

Subjects

Classification

JEL (Journal of Economic Literature) Classification

Description

  • Abstract

    We predict university dropout using random forests based on conditional inference trees and on a broad German data set covering a wide range of aspects of student life and study courses. We model the dropout decision as a binary classification (graduate or dropout) and focus on very early prediction of student dropout by stepwise modeling students’ transition from school (pre-study) over the study-decision phase (decision phase) to the first semesters at university (early study phase). We evaluate how predictive performance changes over the three models, and observe a substantially increased performance when including variables from the first study experiences, resulting in an AUC (area under the curve) of 0.86. Important predictors are the final grade at secondary school, and also determinants associated with student satisfaction and their subjective academic self-concept and self-assessment. A direct outcome of this research is the provision of information to universities wishing to implement early warning systems and more personalized counseling services to support students at risk of dropping out during an early stage of study.

Relations

Related Identifiers

  • Has part
    URL: https://journaldata.zbw.eu/dataset/d25f2ee2-0f67-4ae7-a246-2a85151c9c1d/resource/b3ec2893-2069-4969-aa29-bd92eab27944/download/data-description.xlsx
  • Has part
    URL: https://journaldata.zbw.eu/dataset/d25f2ee2-0f67-4ae7-a246-2a85151c9c1d/resource/3fdc36ff-b5c5-44b2-92d5-b7a1a5d2d573/download/r-codes.r
  • Has part
    URL: https://journaldata.zbw.eu/dataset/d25f2ee2-0f67-4ae7-a246-2a85151c9c1d/resource/9c43bfee-c226-49d1-aa46-3682feb19f09/download/data-access.pdf
  • Has part
    URL: https://journaldata.zbw.eu/dataset/d25f2ee2-0f67-4ae7-a246-2a85151c9c1d/resource/c2f12742-a05b-463f-8a8b-3effaf6fd610/download/readme.pdf

Publications

  • Behr, A., Giese, M., Teguim Kamdjou, H., Theune, K. (2019). Journal of Economics and Statistics, 240(6), 743-789.
    • ID: 10.1515/jbnst-2019-0006 (DOI)

Update Metadata: 2020-10-28 | Issue Number: 1 | Registration Date: 2020-10-28