Building and Using Multiple Stacks of Models for the Classification of Learners and Custom Recommending of Quizzes

Recommending quizzes in e-Learning systems always represents a challenging task, as the quality of recommendations may have high impact on student’s progress. We propose data analysis workflow based building multiple stacks models that use information from former students’ taken quizzes. The current implementation uses RandomForest algorithm for real-world dataset has been obtained controlled environment. As preprocessing techniques, we used normalization and discretization such training classification regression tasks. At run-time, are queried classifying student inferring an optimal quiz is personalized student. evaluated accuracy parametrized previous number found possible timeframe each class students should be provide more helpful