Research On The Application Of Teaching Quality Monitoring In Colleges And Universities Based On Data Mining Technology

With the development of modern technology,the informatization and digitization of education and teaching have become an indispensable part of modern education development.A large amount of valuable data has also been accumulated in the teaching system of universities,but these data have not been well utilized by universities.Data mining technology is a widely used technology in various fields at present,which has significant effects on improving management efficiency and economic benefits.Many universities have also applied data mining technology to teaching,scientific research,and decision-making management.It can analyze and process single data through mining technology and discover valuable information,which not only greatly reduces the time for analyzing data,and it also improves the utilization of data.This paper mainly studies the use of various data mining methods to conduct in-depth analysis of collected teaching quality monitoring data through a data mining platform,and discusses its application in teaching quality monitoring.The main content includes:1.Using the K-means algorithm to classify the standardized evaluation indicators data of Z,and ultimately achieving good clustering results by determining the number of clusters and the equivalence of class center points.The experimental results show that clustering can automatically group teachers with the same or similar teaching abilities,which provides a basis for teachers of different categories to take corresponding measures to develop plans to improve teaching quality;Then,the Apriori algorithm is used to perform correlation analysis on the relevant attributes and evaluation levels of teachers.The classification of each indicator data level is based on the mean of the classification center point.The experimental results show that using this technical route can better analyze the internal factors of teachers that affect teaching quality,providing a reference basis for improving teaching quality.2.Using factor analysis to comprehensively evaluate performance data,and comparing the comprehensive evaluation ranking with the traditional average score ranking.The experimental results show that students with high average scores in the traditional ranking may not necessarily stand out in the comprehensive evaluation score,and the comprehensive evaluation obtained from factor analysis can better reflect the overall professional ability of students;The decision tree C5.0 algorithm is also used to predict the future course scores through the existing student course scores,in which the sorting quantization method is used to partition the student score data,and then the discretization processing is carried out.Finally,the C5.0algorithm is used to predict the students’ future course scores.The experimental results show that the accuracy of using this algorithm to predict the future course scores is 74.07%,This serves as a good warning and reminder for students in their learning.