Research and application of improved k-means algorithm based on educational big data

This paper aims to conduct in-depth mining of student performance data. It is helpful to provide teachers with teaching strategies and improve teaching quality. Compared with the previous research on the k-means algorithm, the main innovation of this paper lies in the selection of the initial cluster center and providing teaching strategies for universities. First, we collect the students' transcripts of three subjects and process the original data including cleaning data, extracting key fields, and integrated processing of data. Then, we use the k-means algorithm, to get the cluster center and the category. Finally, we visualized the clustering results.