The amount of perceived program success is ranked by the students who commit to the fulfillment of expectations for the program. It levels the rank satisfaction and importance of the primary usage program offered. The students acknowledge the approaches to measuring student success which is expected to pass/fail the program. Here it is recognized with the virtual learning environment interactions with the course information followed by the assessment and the marks given with respect to the tutor-given marks (TMA) and computer-graded marks (CMA) with the final exam. Here the model is to predict learning failures and the withdrawal of a student from the module presentation and some of the feature engineering has been done along with recommendations for further features that could be useful for this project. Few classification and regression models are employed to forecast student academic performance. This would give a student performance rate and give the failure rate to find out the risk. The best model for the regression task was Gradient with cross-validation of 4 folds and the best model for the classification task was the support vector machine classifier with a seventy-eight percent accuracy score.
primary usage, virtual learning environment, TMA, CMA
IRE Journals:
C Uthej , Lokesh C K
"A Machine Learning Model to Predict Student Performance Rate" Iconic Research And Engineering Journals Volume 6 Issue 10 2023 Page 437-445
IEEE:
C Uthej , Lokesh C K
"A Machine Learning Model to Predict Student Performance Rate" Iconic Research And Engineering Journals, 6(10)