Predicting student attrition with data mining methods

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Affecting university rankings, school reputation, and financial well-being, student retention has become one of the most important measures of success for higher education institutions. From the institutional perspective, improving student retention starts with a thorough understanding of the causes behind the attrition. Such an understanding is the basis for accurately predicting at-risk students and appropriately intervening to retain them. In this study, using 8 years of institutional data along with three popular data mining techniques, we developed analytical models to predict freshmen student attrition. Of the three model types (artificial neural networks, decision trees, and logistic regression), artificial neural networks performed the best, with an 81% overall prediction accuracy on the holdout sample. The variable importance analysis of the models revealed that the educational and financial variables are the most important among the predictors used in this study.

Original languageEnglish
Pages (from-to)17-35
Number of pages19
JournalJournal of College Student Retention: Research, Theory and Practice
Volume13
Issue number1
DOIs
StatePublished - 1 Jan 2011
Externally publishedYes

Fingerprint

neural network
student
university ranking
reputation
well-being
logistics
regression
cause
school
education

Cite this

@article{3d672589472e4f9f9f5d65cd51ea998c,
title = "Predicting student attrition with data mining methods",
abstract = "Affecting university rankings, school reputation, and financial well-being, student retention has become one of the most important measures of success for higher education institutions. From the institutional perspective, improving student retention starts with a thorough understanding of the causes behind the attrition. Such an understanding is the basis for accurately predicting at-risk students and appropriately intervening to retain them. In this study, using 8 years of institutional data along with three popular data mining techniques, we developed analytical models to predict freshmen student attrition. Of the three model types (artificial neural networks, decision trees, and logistic regression), artificial neural networks performed the best, with an 81{\%} overall prediction accuracy on the holdout sample. The variable importance analysis of the models revealed that the educational and financial variables are the most important among the predictors used in this study.",
author = "Dursun Delen",
year = "2011",
month = "1",
day = "1",
doi = "10.2190/CS.13.1.b",
language = "English",
volume = "13",
pages = "17--35",
journal = "Journal of College Student Retention: Research, Theory and Practice",
issn = "1521-0251",
publisher = "SAGE Publications Inc.",
number = "1",

}

Predicting student attrition with data mining methods. / Delen, Dursun.

In: Journal of College Student Retention: Research, Theory and Practice, Vol. 13, No. 1, 01.01.2011, p. 17-35.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predicting student attrition with data mining methods

AU - Delen, Dursun

PY - 2011/1/1

Y1 - 2011/1/1

N2 - Affecting university rankings, school reputation, and financial well-being, student retention has become one of the most important measures of success for higher education institutions. From the institutional perspective, improving student retention starts with a thorough understanding of the causes behind the attrition. Such an understanding is the basis for accurately predicting at-risk students and appropriately intervening to retain them. In this study, using 8 years of institutional data along with three popular data mining techniques, we developed analytical models to predict freshmen student attrition. Of the three model types (artificial neural networks, decision trees, and logistic regression), artificial neural networks performed the best, with an 81% overall prediction accuracy on the holdout sample. The variable importance analysis of the models revealed that the educational and financial variables are the most important among the predictors used in this study.

AB - Affecting university rankings, school reputation, and financial well-being, student retention has become one of the most important measures of success for higher education institutions. From the institutional perspective, improving student retention starts with a thorough understanding of the causes behind the attrition. Such an understanding is the basis for accurately predicting at-risk students and appropriately intervening to retain them. In this study, using 8 years of institutional data along with three popular data mining techniques, we developed analytical models to predict freshmen student attrition. Of the three model types (artificial neural networks, decision trees, and logistic regression), artificial neural networks performed the best, with an 81% overall prediction accuracy on the holdout sample. The variable importance analysis of the models revealed that the educational and financial variables are the most important among the predictors used in this study.

UR - http://www.scopus.com/inward/record.url?scp=80051745438&partnerID=8YFLogxK

U2 - 10.2190/CS.13.1.b

DO - 10.2190/CS.13.1.b

M3 - Article

AN - SCOPUS:80051745438

VL - 13

SP - 17

EP - 35

JO - Journal of College Student Retention: Research, Theory and Practice

JF - Journal of College Student Retention: Research, Theory and Practice

SN - 1521-0251

IS - 1

ER -