Early Prediction of Course Grades: Models and Feature Selection
This provides a feasible method for monitoring student progress in blended courses, but it is incremental as it compares existing algorithms on new data.
The paper tackled predicting students' final grades in a blended course using generic features from the first six weeks, finding that Support Vector Machines outperformed other models and improved over a baseline.
In this paper, we compare predictive models for students' final performance in a blended course using a set of generic features collected from the first six weeks of class. These features were extracted from students' online homework submission logs as well as other online actions. We compare the effectiveness of 5 different ML algorithms (SVMs, Support Vector Regression, Decision Tree, Naive Bayes and K-Nearest Neighbor). We found that SVMs outperform other models and improve when compared to the baseline. This study demonstrates feasible implementations for predictive models that rely on common data from blended courses that can be used to monitor students' progress and to tailor instruction.