Content Details | NUML Online Research Repository

Title MACHINE LEARNING BASED STUDENT GRADE PERFORMANCE ANALYSIS

Author(s) ASHI MEHMOOD

Abstract Machine learning algorithms may be able to address the growing difficulty of integrating student-related data for the prediction of student performance in order to make better administrative decisions. Machine learning reviews data mining techniques and provides various models to predict students' performance. The study aims to identify the factors that can improve the students’ performance using machine learning techniques. Machine learning involves various features, and it needs statistical and classification algorithms for better prediction. This study indicates the key factors and predicts student performance with better accuracy based on identified factors. Currently, different studies are using various machine learning techniques to predict students' performance. This research presents a paradigm for evaluating academic achievement in students. In this research, the dataset is carefully chosen which includes demographics, previous academic records, and information related to family background. The data was collected from students of various universities. Due COVID-19, the data was collected through online questionnaires and twenty-four different attributes were selected which were taken from different previous studies after being pre-processed. The study is designed to determine the key attributes influencing the students' performance. Another important part of predication is based on different classifiers having various classification algorithms. The result of this study show that the Support Vector Machine is better than various other algorithms. As a result of this study, student’s performance can be improved by working on the specific features which can improve the quality of education. Furthermore CNN can be used to improve accuracy by collecting more data which can help for better utilization of school systems.

Type Thesis/Dissertation MS

Faculty Engineering and Computer Science

Department Engineering

Language English

Publication Date 2022-01-20

Subject

Publisher

Contributor(s)

Format

Identifier

Source

Relation

Coverage

Rights