Student Enrolment Prediction Model in Higher Education Institution

A Data Mining Approach

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper demonstrates the application of educational data mining in predicting applicant’s enrollment decision for academic programme in higher learning institution. This research specifically aims to address the application of data mining on higher education institution database to understand student enrolment data and gaining insights into the important factors in making enrollment decision. By adapting the five phases of the Cross Industry Standard Process for Data Mining (CRISP-DM) process model, detail explanations of the activities conducted to execute the data analytics project are discussed. Predictive models such as logistic regression, decision tree and naïve bayes were built and applied to process the data set. Subsequently, these models were tested for accuracy using 10-fold cross validation. Results show that, given adequate data and appropriate variables, these models are capable of predicting applicant’s enrollment decision with roughly 70% accuracy. It is noted that decision tree model yields the highest accuracy among the three prediction models. In addition, different significant factors are identified for different type of academic programmes applied as suggested by the findings.

Original languageEnglish
Title of host publicationProceedings of the 3rd International Symposium of Information and Internet Technology SYMINTECH 2018
EditorsMohd Azlishah Othman, Mohamad Zoinol Abidin Abd Aziz, Mohd Shakir Md Saat, Mohamad Harris Misran
PublisherSpringer Verlag
Pages43-52
Number of pages10
ISBN (Print)9783030207168
DOIs
Publication statusPublished - 01 Jan 2019
Event3rd International Symposium of Information and Internet Technology, SYMINTECH 2018 - Langkawi, Malaysia
Duration: 18 Dec 201820 Dec 2018

Publication series

NameLecture Notes in Electrical Engineering
Volume565
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference3rd International Symposium of Information and Internet Technology, SYMINTECH 2018
CountryMalaysia
CityLangkawi
Period18/12/1820/12/18

Fingerprint

Data mining
Education
Students
Decision trees
Logistics
Decision making
Industry

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Cite this

Ab Ghani, N. L., Che Cob, Z., Mohd Drus, S., & Sulaiman, H. (2019). Student Enrolment Prediction Model in Higher Education Institution: A Data Mining Approach. In M. A. Othman, M. Z. A. Abd Aziz, M. S. Md Saat, & M. H. Misran (Eds.), Proceedings of the 3rd International Symposium of Information and Internet Technology SYMINTECH 2018 (pp. 43-52). (Lecture Notes in Electrical Engineering; Vol. 565). Springer Verlag. https://doi.org/10.1007/978-3-030-20717-5_6
Ab Ghani, Nur Laila ; Che Cob, Zaihisma ; Mohd Drus, Sulfeeza ; Sulaiman, Hidayah. / Student Enrolment Prediction Model in Higher Education Institution : A Data Mining Approach. Proceedings of the 3rd International Symposium of Information and Internet Technology SYMINTECH 2018. editor / Mohd Azlishah Othman ; Mohamad Zoinol Abidin Abd Aziz ; Mohd Shakir Md Saat ; Mohamad Harris Misran. Springer Verlag, 2019. pp. 43-52 (Lecture Notes in Electrical Engineering).
@inproceedings{0e090edfe7b342db8745e56a2934b1ba,
title = "Student Enrolment Prediction Model in Higher Education Institution: A Data Mining Approach",
abstract = "This paper demonstrates the application of educational data mining in predicting applicant’s enrollment decision for academic programme in higher learning institution. This research specifically aims to address the application of data mining on higher education institution database to understand student enrolment data and gaining insights into the important factors in making enrollment decision. By adapting the five phases of the Cross Industry Standard Process for Data Mining (CRISP-DM) process model, detail explanations of the activities conducted to execute the data analytics project are discussed. Predictive models such as logistic regression, decision tree and na{\"i}ve bayes were built and applied to process the data set. Subsequently, these models were tested for accuracy using 10-fold cross validation. Results show that, given adequate data and appropriate variables, these models are capable of predicting applicant’s enrollment decision with roughly 70{\%} accuracy. It is noted that decision tree model yields the highest accuracy among the three prediction models. In addition, different significant factors are identified for different type of academic programmes applied as suggested by the findings.",
author = "{Ab Ghani}, {Nur Laila} and {Che Cob}, Zaihisma and {Mohd Drus}, Sulfeeza and Hidayah Sulaiman",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-030-20717-5_6",
language = "English",
isbn = "9783030207168",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "43--52",
editor = "Othman, {Mohd Azlishah} and {Abd Aziz}, {Mohamad Zoinol Abidin} and {Md Saat}, {Mohd Shakir} and Misran, {Mohamad Harris}",
booktitle = "Proceedings of the 3rd International Symposium of Information and Internet Technology SYMINTECH 2018",
address = "Germany",

}

Ab Ghani, NL, Che Cob, Z, Mohd Drus, S & Sulaiman, H 2019, Student Enrolment Prediction Model in Higher Education Institution: A Data Mining Approach. in MA Othman, MZA Abd Aziz, MS Md Saat & MH Misran (eds), Proceedings of the 3rd International Symposium of Information and Internet Technology SYMINTECH 2018. Lecture Notes in Electrical Engineering, vol. 565, Springer Verlag, pp. 43-52, 3rd International Symposium of Information and Internet Technology, SYMINTECH 2018, Langkawi, Malaysia, 18/12/18. https://doi.org/10.1007/978-3-030-20717-5_6

Student Enrolment Prediction Model in Higher Education Institution : A Data Mining Approach. / Ab Ghani, Nur Laila; Che Cob, Zaihisma; Mohd Drus, Sulfeeza; Sulaiman, Hidayah.

Proceedings of the 3rd International Symposium of Information and Internet Technology SYMINTECH 2018. ed. / Mohd Azlishah Othman; Mohamad Zoinol Abidin Abd Aziz; Mohd Shakir Md Saat; Mohamad Harris Misran. Springer Verlag, 2019. p. 43-52 (Lecture Notes in Electrical Engineering; Vol. 565).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Student Enrolment Prediction Model in Higher Education Institution

T2 - A Data Mining Approach

AU - Ab Ghani, Nur Laila

AU - Che Cob, Zaihisma

AU - Mohd Drus, Sulfeeza

AU - Sulaiman, Hidayah

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This paper demonstrates the application of educational data mining in predicting applicant’s enrollment decision for academic programme in higher learning institution. This research specifically aims to address the application of data mining on higher education institution database to understand student enrolment data and gaining insights into the important factors in making enrollment decision. By adapting the five phases of the Cross Industry Standard Process for Data Mining (CRISP-DM) process model, detail explanations of the activities conducted to execute the data analytics project are discussed. Predictive models such as logistic regression, decision tree and naïve bayes were built and applied to process the data set. Subsequently, these models were tested for accuracy using 10-fold cross validation. Results show that, given adequate data and appropriate variables, these models are capable of predicting applicant’s enrollment decision with roughly 70% accuracy. It is noted that decision tree model yields the highest accuracy among the three prediction models. In addition, different significant factors are identified for different type of academic programmes applied as suggested by the findings.

AB - This paper demonstrates the application of educational data mining in predicting applicant’s enrollment decision for academic programme in higher learning institution. This research specifically aims to address the application of data mining on higher education institution database to understand student enrolment data and gaining insights into the important factors in making enrollment decision. By adapting the five phases of the Cross Industry Standard Process for Data Mining (CRISP-DM) process model, detail explanations of the activities conducted to execute the data analytics project are discussed. Predictive models such as logistic regression, decision tree and naïve bayes were built and applied to process the data set. Subsequently, these models were tested for accuracy using 10-fold cross validation. Results show that, given adequate data and appropriate variables, these models are capable of predicting applicant’s enrollment decision with roughly 70% accuracy. It is noted that decision tree model yields the highest accuracy among the three prediction models. In addition, different significant factors are identified for different type of academic programmes applied as suggested by the findings.

UR - http://www.scopus.com/inward/record.url?scp=85066119895&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066119895&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-20717-5_6

DO - 10.1007/978-3-030-20717-5_6

M3 - Conference contribution

SN - 9783030207168

T3 - Lecture Notes in Electrical Engineering

SP - 43

EP - 52

BT - Proceedings of the 3rd International Symposium of Information and Internet Technology SYMINTECH 2018

A2 - Othman, Mohd Azlishah

A2 - Abd Aziz, Mohamad Zoinol Abidin

A2 - Md Saat, Mohd Shakir

A2 - Misran, Mohamad Harris

PB - Springer Verlag

ER -

Ab Ghani NL, Che Cob Z, Mohd Drus S, Sulaiman H. Student Enrolment Prediction Model in Higher Education Institution: A Data Mining Approach. In Othman MA, Abd Aziz MZA, Md Saat MS, Misran MH, editors, Proceedings of the 3rd International Symposium of Information and Internet Technology SYMINTECH 2018. Springer Verlag. 2019. p. 43-52. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-3-030-20717-5_6