Introduction (Prediction of Student Final Exam Performance in an Introductory Programming Course: Development and Validation of the Use of a Support Vector Machine-Regression Model)
Improving student knowledge and performance is one of the most important concerns at the universities. One way would be to predict the student performances in the future and identify and help the students who are at risk of course failure. Programming is essential course to computer science or IT curricula. This courses are one of the toughest ones for the novices and it is important to identify factors that influence student performance. In this paper the authors use data that was collected from introductory course in 2012-2016 from the ViLLE platform, that is e-learning tool. They have two research questions:
-
What is the optimal combination of predictor/independent variables with the highest prediction accuracy for predicting student’s academic performance?
-
What is the percentage of academically at-risk students that can be correctly identified by the model? They used SVM-regression (support vector machine) algorithm as a model.
0
1
Tags
Data Science
Related
Introduction (Prediction of Student Final Exam Performance in an Introductory Programming Course: Development and Validation of the Use of a Support Vector Machine-Regression Model)
Literature Review (Prediction of Student Final Exam Performance in an Introductory Programming Course: Development and Validation of the Use of a Support Vector Machine-Regression Model)
Research Method (Prediction of Student Final Exam Performance in an Introductory Programming Course: Development and Validation of the Use of a Support Vector Machine-Regression Model)
Data Analysis and the Results (Prediction of Student Final Exam Performance in an Introductory Programming Course: Development and Validation of the Use of a Support Vector Machine-Regression Model)
Discussion