Abstract:
Predictive analytics applications have become essential in higher education institutions for generating high-quality performance insights and data using advanced analytics and machine learning techniques. Student grades are widely recognized as a crucial performance indicator that aids educators in monitoring academic progress. Researchers have explored various machine learning approaches for predicting student grades in the field of education. This study focuses on enhancing predictive accuracy by analyzing machine learning algorithms to forecast final student grades in first-semester courses. Two modules are highlighted: assessing accuracy performance using popular machine learning approaches (Decision Tree, Support Vector Machine, Naive Bayes, K-Nearest Neighbor, Logistic Regression, and Random Forest) on a dataset of 1282 real student course grades, and proposing a multiclass prediction model that addresses challenges related to imbalanced datasets through the Synthetic Minority Oversampling Technique (SMOTE) and feature selection techniques. The results demonstrate the model's ability to integrate with Random Forest and achieve a significant improvement with an f-measure of 99.5% in predicting student grades. This project aligns with the requirements of final year engineering projects in computer science and offers an opportunity to work on an IEEE project.
Components provided by our project center in Bangalore include:
Comprehensive documentation support for your final year engineering project
Implementation of working hardware/software in your project environment
Specialized guidance and classes for IEEE projects and final year projects in computer science
Assistance with selecting and developing IEEE projects for CSE
Access to a final year project center in Bangalore for additional support and resources
Contact our project center in Bangalore to explore exciting opportunities for your BTech final year project in the domain of student score prediction using machine learning and IEEE projects in computer science.