STUDENT’S PERFORMANCE PREDICTION USING EDUCATIONAL DATA MINING

QUAH, MIN QI (2020) STUDENT’S PERFORMANCE PREDICTION USING EDUCATIONAL DATA MINING. [Final Year Project] (Submitted)

[thumbnail of 24623_Quah Min Qi.pdf] PDF
24623_Quah Min Qi.pdf
Restricted to Registered users only

Download (2MB)

Abstract

Every educational institution generates a large amount of data related to the registered
students. If that data is not analyzed and used for useful purposes, then all efforts will be
wasted as there is no future use of the data occurring. Academic institutions such as
universities, colleges and schools usually do not have tools or process flow that uses the
big data from the systems (e.g. enrollment and performance systems) to perform
prediction on student’s performance. By using the big data, academic institutions shall be
able to predict student’s performance for strategic decision making (e.g. improve current
teaching model, identify low performing students etc.). The most used technique for
prediction is educational data mining. This study is conducted with the aim to better
understand educational data mining.
The main objective of this study is to appropriate educational data mining techniques and
select suitable technique(s) to implement analyses and prediction on the big data obtained.
The method that used to conduct this study is design science. The outcome of this study
is acquiring which classification method has the highest accuracy in predicting student’s
performance and visualizing the prediction results in a Power BI Dashboard. The findings
of this study may contribute towards the improvement of educational institution’s
teaching models and student performance.

Item Type: Final Year Project
Subjects: Q Science > Q Science (General)
Departments / MOR / COE: Sciences and Information Technology > Computer and Information Sciences
Depositing User: Mr Ahmad Suhairi Mohamed Lazim
Date Deposited: 23 Sep 2021 23:43
Last Modified: 23 Sep 2021 23:43
URI: http://utpedia.utp.edu.my/id/eprint/21718

Actions (login required)

View Item
View Item