Application of Data Mining in the Analysis of College Students' Grades

With the explosive growth of data, the digitali-zation process of universities is also steadily advancing. It also becomes particularly important to carry out personalized teaching management for college students according to their grades. To address this issue, we selected the grades related to mathematics students of the classes of 2011–2018 from the academic affairs system of a university as data samples. Firstly, we use the SIMLR clustering algorithm to analyze the students' grades. This algorithm can reasonably choose the distance metric by learning multiple kernels according to the characteristics of the grade data. Secondly, we applied the Apriori algorithm to mine association rules to analyze the students' major course grade data and semester grade data. We mine the characteristics of students in different grade groups using clustering, and we mine the connections between courses and courses, semesters and semesters using association analysis to obtain information that helps students learn, providing theoretical reference and decision basis for school scheduling and teacher teaching, and improving college students' academic performance.