Comparative Analysis of Machine Learning Models for Students’ Performance Prediction

Leila Ismail; Huned Materwala; Alain Hennebelle

doi:10.1007/978-3-030-71782-7_14

Comparative Analysis of Machine Learning Models for Students’ Performance Prediction

Leila Ismail, Huned Materwala, Alain Hennebelle

Department of Computer Science and Software Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

18 Citations (Scopus)

Abstract

Machine learning for education is an emerging discipline where a model is developed based on training data to make predictions on students’ performance. The main aim is to identify students who would have difficulty in their learning and to take precautionary measures to help them. In this paper, we conduct a comparative analysis of the most used machine learning classification models in the literature. We evaluate the performance of the models in terms of accuracy, F-measure, and execution time using two real-life education datasets. The performance of the models is data-driven. We give insights into the models’ performance and advise on the best model to use accordingly. We believe the results of this paper will be widely used by education professionals for accurate predictions.

Original language	English
Title of host publication	Advances in Digital Science - ICADS 2021
Editors	Tatiana Antipova
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	149-160
Number of pages	12
ISBN (Print)	9783030717810
DOIs	https://doi.org/10.1007/978-3-030-71782-7_14
Publication status	Published - 2021
Event	International Conference on Advances in Digital Science, ICADS 2021 - Salvador, Brazil Duration: Feb 19 2021 → Feb 21 2021

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1352
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	International Conference on Advances in Digital Science, ICADS 2021
Country/Territory	Brazil
City	Salvador
Period	2/19/21 → 2/21/21

Keywords

Artificial intelligence
Classification models
Educational data mining
Educational machine learning
Student performance prediction

ASJC Scopus subject areas

Control and Systems Engineering
General Computer Science

Access to Document

10.1007/978-3-030-71782-7_14

Cite this

Ismail, L., Materwala, H., & Hennebelle, A. (2021). Comparative Analysis of Machine Learning Models for Students’ Performance Prediction. In T. Antipova (Ed.), Advances in Digital Science - ICADS 2021 (pp. 149-160). (Advances in Intelligent Systems and Computing; Vol. 1352). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-71782-7_14

Comparative Analysis of Machine Learning Models for Students’ Performance Prediction. / Ismail, Leila; Materwala, Huned; Hennebelle, Alain.
Advances in Digital Science - ICADS 2021. ed. / Tatiana Antipova. Springer Science and Business Media Deutschland GmbH, 2021. p. 149-160 (Advances in Intelligent Systems and Computing; Vol. 1352).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ismail, L, Materwala, H & Hennebelle, A 2021, Comparative Analysis of Machine Learning Models for Students’ Performance Prediction. in T Antipova (ed.), Advances in Digital Science - ICADS 2021. Advances in Intelligent Systems and Computing, vol. 1352, Springer Science and Business Media Deutschland GmbH, pp. 149-160, International Conference on Advances in Digital Science, ICADS 2021, Salvador, Brazil, 2/19/21. https://doi.org/10.1007/978-3-030-71782-7_14

@inproceedings{2d89b2f6f99841da896af3653eafd450,

title = "Comparative Analysis of Machine Learning Models for Students{\textquoteright} Performance Prediction",

abstract = "Machine learning for education is an emerging discipline where a model is developed based on training data to make predictions on students{\textquoteright} performance. The main aim is to identify students who would have difficulty in their learning and to take precautionary measures to help them. In this paper, we conduct a comparative analysis of the most used machine learning classification models in the literature. We evaluate the performance of the models in terms of accuracy, F-measure, and execution time using two real-life education datasets. The performance of the models is data-driven. We give insights into the models{\textquoteright} performance and advise on the best model to use accordingly. We believe the results of this paper will be widely used by education professionals for accurate predictions.",

keywords = "Artificial intelligence, Classification models, Educational data mining, Educational machine learning, Student performance prediction",

author = "Leila Ismail and Huned Materwala and Alain Hennebelle",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.; International Conference on Advances in Digital Science, ICADS 2021 ; Conference date: 19-02-2021 Through 21-02-2021",

year = "2021",

doi = "10.1007/978-3-030-71782-7_14",

language = "English",

isbn = "9783030717810",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "149--160",

editor = "Tatiana Antipova",

booktitle = "Advances in Digital Science - ICADS 2021",

}

TY - GEN

T1 - Comparative Analysis of Machine Learning Models for Students’ Performance Prediction

AU - Ismail, Leila

AU - Materwala, Huned

AU - Hennebelle, Alain

PY - 2021

Y1 - 2021

N2 - Machine learning for education is an emerging discipline where a model is developed based on training data to make predictions on students’ performance. The main aim is to identify students who would have difficulty in their learning and to take precautionary measures to help them. In this paper, we conduct a comparative analysis of the most used machine learning classification models in the literature. We evaluate the performance of the models in terms of accuracy, F-measure, and execution time using two real-life education datasets. The performance of the models is data-driven. We give insights into the models’ performance and advise on the best model to use accordingly. We believe the results of this paper will be widely used by education professionals for accurate predictions.

AB - Machine learning for education is an emerging discipline where a model is developed based on training data to make predictions on students’ performance. The main aim is to identify students who would have difficulty in their learning and to take precautionary measures to help them. In this paper, we conduct a comparative analysis of the most used machine learning classification models in the literature. We evaluate the performance of the models in terms of accuracy, F-measure, and execution time using two real-life education datasets. The performance of the models is data-driven. We give insights into the models’ performance and advise on the best model to use accordingly. We believe the results of this paper will be widely used by education professionals for accurate predictions.

KW - Artificial intelligence

KW - Classification models

KW - Educational data mining

KW - Educational machine learning

KW - Student performance prediction

UR - http://www.scopus.com/inward/record.url?scp=85103510999&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85103510999&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-71782-7_14

DO - 10.1007/978-3-030-71782-7_14

M3 - Conference contribution

AN - SCOPUS:85103510999

SN - 9783030717810

T3 - Advances in Intelligent Systems and Computing

SP - 149

EP - 160

BT - Advances in Digital Science - ICADS 2021

A2 - Antipova, Tatiana

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Conference on Advances in Digital Science, ICADS 2021

Y2 - 19 February 2021 through 21 February 2021

ER -

Comparative Analysis of Machine Learning Models for Students’ Performance Prediction

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this