Evaluating Student Knowledge Assessment Using Machine Learning Techniques

The process of learning about a student’s knowledge and comprehension particular subject is referred to as student assessment. It helps identify areas where students need additional support or challenge can be used evaluate the effectiveness instruction, make important decisions such on placement curriculum development, monitor quality education. Evaluating assessment essential measuring progress, informing providing feedback improve performance enhance overall teaching experience. This research paper designed create machine (ML)-based system that assesses throughout course their studies pinpoints key variables have most significant effects expertise. Additionally, it describes impact running models with data only contains features performance. To classify students, employs seven different classifiers, including vector machines (SVM), logistic regression (LR), random forest (RF), decision tree (DT), gradient boosting (GBM), Gaussian Naive Bayes (GNB), multi-layer perceptron (MLP). carries out two experiments see how best replicate automatic classification knowledge. In first experiment, dataset (Dataset 1) was in its original state, all five properties listed dataset, indicators. second least correlated variable removed from smaller 2), same set indicators evaluated. Then, using Dataset 1 2 were compared. GBM exhibited highest prediction accuracy 98%, according 1. terms error, also performed well. optimistic forecasts performance, denoted indicator ‘precision’, at 99%, while DT, RF, SVM 98% accurate for experiment’s findings demonstrated practically no classifiers showed appreciable improvements reduced feature 2. time required related objects level corresponding goal object less impact.