Predictive Modeling of Quiz Question Performance using Preceding Quiz Activities and Machine Learning

This study explores the relationship between quiz question performance and preceding quiz activities, aiming to predict the former through the lens of diverse machine learning models. Our research explores four distinct approaches, namely Logistic Regression, Gradient Boosted Trees, Extreme Gradient Boosted Trees, and Gaussian Naïve Bayes classifiers. By extracting 76 variables from the LMS log files and employing a dataset comprising the data of 455 students, we conducted an investigation categorizing quiz question performance into two classes: accurately and incorrectly answered. The predictive potential of the selected machine learning models was evaluated through metrics including accuracy, precision, recall, and fl-score. Our findings reveal that Logistic Regression and XGBoost achieved the highest prediction accuracy rates of 81.8% and 80.5%, respectively.