A WEB-BASED SYSTEM FOR THE PREDICTION OF STUDENT PERFORMANCE IN UPCOMING PUBLIC EXAMS BASED ON ACADEMIC RECORDS

DELLON, NELSON BRUNNIE (2023) A WEB-BASED SYSTEM FOR THE PREDICTION OF STUDENT PERFORMANCE IN UPCOMING PUBLIC EXAMS BASED ON ACADEMIC RECORDS. [Final Year Project Report] (Unpublished)

PDF (Please get the password by email to repository@unimas.my , or call ext: 082-583914/3973/3933) DELLON ft.pdf Restricted to Registered users only Download (6MB)

Abstract

Structured examination systems are used by educational institutions all around the world to assess the performance of students at a given point in their study. Public exam systems which are a type of structured examination systems are implemented nationwide at institutions in nations that place a high value on education. The government of Malaysia had imposed this system on elementary students with their Ujian Penilaian Sekolah Rendah and secondary students with their Sijil Pelajaran Malaysia and Pentaksiran Tingkatan 3. There are several methods already in place that Kementerian Pelajaran Malaysia(KPM) offers. All of these technologies were created by developers to guarantee the efficiency of the teaching process for pupils. In addition to digitalizing the educational system, these systems will aid instructors in their day-to-day instruction. However, there is no limited mechanism in place to help teachers anticipate and correctly forecast the outcomes of their students' tests. Both students and teachers will be substantially better prepared for the forthcoming exam if a system exists that can reliably anticipate a student's mark in their future exams, particularly public exams. The goal of this study is to properly anticipate students' impending grades. Teachers will be able to precisely forecast their students' impending grades utilizing the system's web-based application integration and machine learning algorithms. The machine learning algorithms that will be used and compared are Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), and Linear Regression (LR). All of these algorithms will be cross validate using Mean Absolute Error (MAE) in order to compare all of the accuracies of the algorithms.

Actions (For repository members only: login required)

View Item