Stacking Classifiers for Early Detection of Students at Risk

Eitel J. M. Lauría, Edward Presutti, Maria Kapogiannis, Anuya Kamath

2018

Abstract

A stacked ensemble is a machine learning method that involves training a second stage learner to find the optimal combination of a collection of based learners. This paper provides a methodology to create a stacked ensemble of classifiers to perform early detection of academically at-risk students and shows how to organize the data for training and testing at each stage of the stacked ensemble architecture. Experimental tests are carried out using college-wide data, to demonstrate how the stack can be used for prediction.

Paper Citation

in Harvard Style

Lauría E., Presutti E., Kapogiannis M. and Kamath A. (2018). Stacking Classifiers for Early Detection of Students at Risk.In Proceedings of the 10th International Conference on Computer Supported Education - Volume 1: CSEDU, ISBN 978-989-758-291-2, pages 390-397. DOI: 10.5220/0006781203900397

in Bibtex Style

@conference{csedu18,
author={Eitel J. M. Lauría and Edward Presutti and Maria Kapogiannis and Anuya Kamath},
title={Stacking Classifiers for Early Detection of Students at Risk},
booktitle={Proceedings of the 10th International Conference on Computer Supported Education - Volume 1: CSEDU,},
year={2018},
pages={390-397},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006781203900397},
isbn={978-989-758-291-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Computer Supported Education - Volume 1: CSEDU,
TI - Stacking Classifiers for Early Detection of Students at Risk
SN - 978-989-758-291-2
AU - Lauría E.
AU - Presutti E.
AU - Kapogiannis M.
AU - Kamath A.
PY - 2018
SP - 390
EP - 397
DO - 10.5220/0006781203900397