APRIORI ALGORITHM TO ANALYSE STUDENTS PERFORMANCE

Abstract— Predicting academic accomplishment is a critical goal in the field of education as it can reveal the elements that determine the degree to which a student performs and recommend activities that enhance learning outcomes. In this research, we offer a method for analyzing student performance that makes use of association rule mining and the Apriori algorithm. We develop frequent item sets and association rules that can be used to spot patterns and interactions between various parameters using information from a dataset of student performance, including grade point averages, comments, and language preferences. In order to group students according to their performance in the data set, we additionally use performance level categories. We then employ our strategy to rank the best 5, worst, and average pupils using association rules. Our findings demonstrate that this method is useful for spotting trends and connections between various variables and can be applied to forecast student performance. We come to the conclusion that interventions aiming at enhancing student performance and learning outcomes may be informed by our methodology