INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Today, there is a growing demand for predictive analytics applications in higher education institutions. These applications utilize advanced analytics, including machine learning, to extract valuable insights and improve performance across all levels of education. Student grades are a crucial performance indicator that educators use to track academic progress. Over the past decade, various machine learning techniques have been proposed for educational purposes. However, challenges persist in dealing with imbalanced datasets to enhance the accuracy of predicting student grades. This study offers a detailed analysis of machine learning techniques to predict final student grades in first-semester courses, aiming to boost predictive accuracy. The paper focuses on two main modules. Firstly, it compares the performance of six popular machine learning techniques - Decision Tree (J48), Support Vector Machine (SVM), Naïve Bayes (NB), K-Nearest Neighbor (kNN ), Logistic Regression (LR), and Random Forest (RF) - using a dataset of 1282 real student course grades. Secondly, a multiclass prediction model is proposed to address overfitting and misclassification issues in imbalanced multi-class scenarios, employing oversampling techniques like Synthetic Minority Oversampling Technique (SMOTE) along with feature selection methods. The results demonstrate that integrating the proposed model with RF leads to a significant improvement, achieving the highest f-measure of 99.5%. This model shows promising results in enhancing prediction performance for imbalanced multi-class student grade prediction.
Keywords:
SVM, NB, KNN, LR, RF.
Cite Article:
"MULTICLASS PREDECTION MODEL FOR STUDENTS GRADE PREDECTION USING MACHINE LEARNING", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.9, Issue 3, page no.832 - 836, March-2024, Available :http://www.ijsdr.org/papers/IJSDR2403117.pdf
Downloads:
000337363
Publication Details:
Published Paper ID: IJSDR2403117
Registration ID:210531
Published In: Volume 9 Issue 3, March-2024
DOI (Digital Object Identifier):
Page No: 832 - 836
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn