Abstract
This capstone project addresses the challenge of students' lack of awareness regarding their academic performance and potential grade declines throughout the semester. The project aims to develop a predictive model that offers students timely warnings about their predicted grades, enabling them to take proactive measures to improve their academic performance. Utilizing the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology, the project analyzes a comprehensive dataset comprising student demographics, curriculum history, and grades in various subjects. The model undergoes rigorous evaluation and validation to ensure its effectiveness in predicting students' academic outcomes accurately. The findings reveal that the linear regression model demonstrates the highest accuracy among the models considered, achieving an impressive accuracy rate of 93%. A detailed analysis of the model's performance indicates remarkable accuracy, consistency, and a strong fit to the dataset. These findings underscore the effectiveness of the linear regression model in accurately predicting students' academic performance and highlight its suitability for achieving the project's objectives. Overall, this project contributes to enhancing students' awareness of their academic standing and provides them with actionable insights to improve their academic outcomes.
Publication Date
4-16-2023
Document Type
Master's Project
Student Type
Graduate
Degree Name
Professional Studies (MS)
Department, Program, or Center
Graduate Programs & Research
Advisor
Ioannis Karamitsos
Recommended Citation
Al-Obaidi, Hameed, "Student Grade Prediction using Machine Learning Methods" (2023). Thesis. Rochester Institute of Technology. Accessed from
https://repository.rit.edu/theses/12213
Campus
RIT Dubai
