A comparative analysis of machine learning techniques for student retention management

Research output: Contribution to journalArticle

78 Citations (Scopus)

Abstract

Student retention is an essential part of many enrollment management systems. It affects university rankings, school reputation, and financial wellbeing. Student retention has become one of the most important priorities for decision makers in higher education institutions. Improving student retention starts with a thorough understanding of the reasons 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 five years of institutional data along with several data mining techniques (both individuals as well as ensembles), we developed analytical models to predict and to explain the reasons behind freshmen student attrition. The comparative analyses results showed that the ensembles performed better than individual models, while the balanced dataset produced better prediction results than the unbalanced dataset. The sensitivity analysis of the models revealed that the educational and financial variables are among the most important predictors of the phenomenon.

Original languageEnglish
Pages (from-to)498-506
Number of pages9
JournalDecision Support Systems
Volume49
Issue number4
DOIs
StatePublished - 1 May 2010
Externally publishedYes

Fingerprint

Learning systems
Students
Educational Models
Data Mining
Sensitivity analysis
Data mining
Analytical models
Education
Machine Learning
Machine learning
Student retention
Comparative analysis
Comparative Analysis
Student Retention
Attrition
Ensemble
Datasets
Financial variables
Analytical model
Enrollment

Keywords

  • Classification
  • Machine learning
  • Prediction
  • Retention management
  • Sensitivity analysis
  • Student attrition

Cite this

@article{0251140f958b4001a6d8db3e650577da,
title = "A comparative analysis of machine learning techniques for student retention management",
abstract = "Student retention is an essential part of many enrollment management systems. It affects university rankings, school reputation, and financial wellbeing. Student retention has become one of the most important priorities for decision makers in higher education institutions. Improving student retention starts with a thorough understanding of the reasons 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 five years of institutional data along with several data mining techniques (both individuals as well as ensembles), we developed analytical models to predict and to explain the reasons behind freshmen student attrition. The comparative analyses results showed that the ensembles performed better than individual models, while the balanced dataset produced better prediction results than the unbalanced dataset. The sensitivity analysis of the models revealed that the educational and financial variables are among the most important predictors of the phenomenon.",
keywords = "Classification, Machine learning, Prediction, Retention management, Sensitivity analysis, Student attrition",
author = "Dursun Delen",
year = "2010",
month = "5",
day = "1",
doi = "10.1016/j.dss.2010.06.003",
language = "English",
volume = "49",
pages = "498--506",
journal = "Decision Support Systems",
issn = "0167-9236",
publisher = "Elsevier",
number = "4",

}

A comparative analysis of machine learning techniques for student retention management. / Delen, Dursun.

In: Decision Support Systems, Vol. 49, No. 4, 01.05.2010, p. 498-506.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A comparative analysis of machine learning techniques for student retention management

AU - Delen, Dursun

PY - 2010/5/1

Y1 - 2010/5/1

N2 - Student retention is an essential part of many enrollment management systems. It affects university rankings, school reputation, and financial wellbeing. Student retention has become one of the most important priorities for decision makers in higher education institutions. Improving student retention starts with a thorough understanding of the reasons 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 five years of institutional data along with several data mining techniques (both individuals as well as ensembles), we developed analytical models to predict and to explain the reasons behind freshmen student attrition. The comparative analyses results showed that the ensembles performed better than individual models, while the balanced dataset produced better prediction results than the unbalanced dataset. The sensitivity analysis of the models revealed that the educational and financial variables are among the most important predictors of the phenomenon.

AB - Student retention is an essential part of many enrollment management systems. It affects university rankings, school reputation, and financial wellbeing. Student retention has become one of the most important priorities for decision makers in higher education institutions. Improving student retention starts with a thorough understanding of the reasons 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 five years of institutional data along with several data mining techniques (both individuals as well as ensembles), we developed analytical models to predict and to explain the reasons behind freshmen student attrition. The comparative analyses results showed that the ensembles performed better than individual models, while the balanced dataset produced better prediction results than the unbalanced dataset. The sensitivity analysis of the models revealed that the educational and financial variables are among the most important predictors of the phenomenon.

KW - Classification

KW - Machine learning

KW - Prediction

KW - Retention management

KW - Sensitivity analysis

KW - Student attrition

UR - http://www.scopus.com/inward/record.url?scp=78049421754&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2010.06.003

DO - 10.1016/j.dss.2010.06.003

M3 - Article

AN - SCOPUS:78049421754

VL - 49

SP - 498

EP - 506

JO - Decision Support Systems

JF - Decision Support Systems

SN - 0167-9236

IS - 4

ER -