The classification-based machine learning algorithm to predict students' knowledge levels

Innovation can give learning coherence in numerous unique situations when understudies cannot be truly present in their study halls. The current innovation and proactive systems are needed to advance a problematic type of schooling that does not make up for the customary learning climate. In any case, there are numerous boundaries to effective remote and internet learning driven by innovation. This research implemented k-mean clustering to a dataset of 146 students-the classification procedure for predicting grade outcomes using the decision tree technique. The attribute with the most significant effect on the classification of the student's grades is. The result is shown the grade property is the root node. This clustering technique acts as a benchmark for evaluating each student's growth and performance throughout their further education.