Data Analysis and Predictive Modeling of Teaching Skill Performance of English Normal College Students Based on K-means Clustering Algorithm

With the continuous development of basic education and the continuous improvement of educational quality requirements, as a qualified normal school graduate or new teacher, in addition to mastering various educational theoretical knowledge, teaching concepts, and teaching methods, it is also necessary to have excellent teaching skills. Research on Data Analysis and Predictive Modeling of Teaching Skill Performance of English Normal University Students Based on K-means Clustering Algorithm is a research that analyzes and predicts the teaching skill performance of English normal university students based on K-means clustering algorithm. The study was conducted by Dr. Zu Yunfeng, a professor at the Department of Computer Science and Technology, Guangxi University, China. This article will outline this research project, its findings, and conclusions. By analyzing and mining behavioral characteristics data such as students’ lives, learning, and activities, an improved K-means clustering algorithm is used to establish a student performance category model, achieving classification of students based on student performance data. Select six attribute data of students’ “moral education scores, physical education scores, intellectual education scores, competition grades, poverty student grades, and scholarship grades” as characteristic evaluation indicators. Aiming at problems such as data duplication, deletion, and inconsistent storage types caused by excessive categories in university student management systems, clean, integrate, and transform the data storage format to obtain input data that meets the K-means algorithm.