Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance

First-year students’ learning performance has received much attention in educational practice and theory. Previous works used some variables, which should be obtained during the course or in the progress of the semester through questionnaire surveys and interviews, to build prediction models. These...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Thao-Trang Huynh-Cam, Long-Sheng Chen, Huynh Le
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	students’ learning performance prediction model random forest (RF) decision tree (DT) feature selection technological and vocational education Industrial engineering. Management engineering T55.4-60.8 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/b2e7c55f69b846f0ad6e1ec1a64bc336
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b2e7c55f69b846f0ad6e1ec1a64bc336
record_format	dspace
spelling	oai:doaj.org-article:b2e7c55f69b846f0ad6e1ec1a64bc3362021-11-25T16:13:08ZUsing Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance10.3390/a141103181999-4893https://doaj.org/article/b2e7c55f69b846f0ad6e1ec1a64bc3362021-10-01T00:00:00Zhttps://www.mdpi.com/1999-4893/14/11/318https://doaj.org/toc/1999-4893First-year students’ learning performance has received much attention in educational practice and theory. Previous works used some variables, which should be obtained during the course or in the progress of the semester through questionnaire surveys and interviews, to build prediction models. These models cannot provide enough timely support for the poor performance students, caused by economic factors. Therefore, other variables are needed that allow us to reach prediction results earlier. This study attempts to use family background variables that can be obtained prior to the start of the semester to build learning performance prediction models of freshmen using random forest (RF), C5.0, CART, and multilayer perceptron (MLP) algorithms. The real sample of 2407 freshmen who enrolled in 12 departments of a Taiwan vocational university will be employed. The experimental results showed that CART outperforms C5.0, RF, and MLP algorithms. The most important features were <i>mother’s occupations</i>, <i>department</i>, <i>father’s occupations</i>, <i>main source of living expenses</i>, and <i>admission status</i>. The extracted knowledge rules are expected to be indicators for students’ early performance prediction so that strategic intervention can be planned before students begin the semester.Thao-Trang Huynh-CamLong-Sheng ChenHuynh LeMDPI AGarticlestudents’ learning performanceprediction modelrandom forest (RF)decision tree (DT)feature selectiontechnological and vocational educationIndustrial engineering. Management engineeringT55.4-60.8Electronic computers. Computer scienceQA75.5-76.95ENAlgorithms, Vol 14, Iss 318, p 318 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	students’ learning performance prediction model random forest (RF) decision tree (DT) feature selection technological and vocational education Industrial engineering. Management engineering T55.4-60.8 Electronic computers. Computer science QA75.5-76.95
spellingShingle	students’ learning performance prediction model random forest (RF) decision tree (DT) feature selection technological and vocational education Industrial engineering. Management engineering T55.4-60.8 Electronic computers. Computer science QA75.5-76.95 Thao-Trang Huynh-Cam Long-Sheng Chen Huynh Le Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance
description	First-year students’ learning performance has received much attention in educational practice and theory. Previous works used some variables, which should be obtained during the course or in the progress of the semester through questionnaire surveys and interviews, to build prediction models. These models cannot provide enough timely support for the poor performance students, caused by economic factors. Therefore, other variables are needed that allow us to reach prediction results earlier. This study attempts to use family background variables that can be obtained prior to the start of the semester to build learning performance prediction models of freshmen using random forest (RF), C5.0, CART, and multilayer perceptron (MLP) algorithms. The real sample of 2407 freshmen who enrolled in 12 departments of a Taiwan vocational university will be employed. The experimental results showed that CART outperforms C5.0, RF, and MLP algorithms. The most important features were <i>mother’s occupations</i>, <i>department</i>, <i>father’s occupations</i>, <i>main source of living expenses</i>, and <i>admission status</i>. The extracted knowledge rules are expected to be indicators for students’ early performance prediction so that strategic intervention can be planned before students begin the semester.
format	article
author	Thao-Trang Huynh-Cam Long-Sheng Chen Huynh Le
author_facet	Thao-Trang Huynh-Cam Long-Sheng Chen Huynh Le
author_sort	Thao-Trang Huynh-Cam
title	Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance
title_short	Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance
title_full	Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance
title_fullStr	Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance
title_full_unstemmed	Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance
title_sort	using decision trees and random forest algorithms to predict and determine factors contributing to first-year university students’ learning performance
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b2e7c55f69b846f0ad6e1ec1a64bc336
work_keys_str_mv	AT thaotranghuynhcam usingdecisiontreesandrandomforestalgorithmstopredictanddeterminefactorscontributingtofirstyearuniversitystudentslearningperformance AT longshengchen usingdecisiontreesandrandomforestalgorithmstopredictanddeterminefactorscontributingtofirstyearuniversitystudentslearningperformance AT huynhle usingdecisiontreesandrandomforestalgorithmstopredictanddeterminefactorscontributingtofirstyearuniversitystudentslearningperformance
_version_	1718413278031380480

Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance

Ejemplares similares