Student Behavior Analysis Research of based on Data Mining

Abstract

University data governance produces a large amount of data, including a large number of student data. How to use data mining technology to analyze and apply student data is the key to improve the scientific management level of the school and the quality of talent training. This paper proposes an adaptive K-means clustering algorithm. Using data mining and big data technology, it selects student consumption, learning, book borrowing, access record and other characteristic data, and conducts data collection, processing and clustering analysis of student behavior data by establishing a characteristic model of student behavior data. The experiment shows that the algorithm used in this paper analyzes the student feature model, and the students who eat regularly and go to the library more often generally have better academic performance. The results of data analysis can be used to predict student performance. Based on the data mining technology, this paper analyzes the data of students’ behavior to realize the prediction and early warning of students’ behavior, which can provide data decision and scientific support for the precise management of schools.