Application and Implementation of Associ-ation Rule Data Mining Technology in Stu-dent Information Management Systems of Colleges and Universities

Abstract

With the aid of association rule mining, this study mines data for student information management systems at the college and university levels and discovers immense importance in the behaviour of students and their academic performance. The dataset will be added with demographic records and the academic records of the students along with extra-curricular activities. Using the Apriori algorithm, this study discovers significant association rules that truly depict trends concerning prevailing combinations of classes, the advantages of high attendance, favourable grade outcomes, and also trends in gender preferences on course selections. Of significance, the findings suggest a robust correlation exists between prevalent class pairings, positive effects associated with attendance on grade attainment, and gender-based propensities with a female bias to prefer engineering programs for males. These findings can assist schools in proposing curricula, student support programs, and resource allocation plans at an optimal time. Such research guides evidence-based decision-making and forms a basis for educational data analytics to facilitate efforts towards improved engagement, success rates, and institutional effectiveness.