Stuay On Online Learing Behaior Analysis And Achievement Prediction Based On Decision Terr

With the rapid development of data mining,using data mining to analyze online learning behavior data is conducive to the construction of smart campus.The construction of smart campus through education data mining has become a major research direction at home and abroad.Comprehensive analysis of online learning behavior data on students through educational big data and decision tree algorithm models to capture student behavior.The prediction of student achievement is crucial for improving the quality of teaching and learning in schools.In view of this,this paper discusses the analysis of student online behavioral data and achievement prediction base d on decision tree algorithm model.Summarizing the findings of the literature review on educational data mining techniques,decision tree algorithm models,student behavior analysis and achievement prediction as a premise.Identifying the reasons,significance,and content of using decision tree algorithm models and data mining techniques to analyze student behavior and performance predictions for this pa per’s.The follow-up research score lays a solid theoretical foundation.This paper collects data based on online learning platform,conducts data processing and correlation analysis of learning behavior data.Based on the learning Access platform system,the learning behavior data generated by freshmen in a university were collected,such as students’ course video score,course video progress,homework score,interview score and task completion.With the help of data mining,this paper studies the correlation between some behavioral data generated by students on the online learning platform and their grades.The correlation between some student-generated behavioral data and student performance in an online learning platform was carried out.Firstly,this paper organizes the statistical student behavior data as follows: course video score and course progress score,assignment score,access score,access score,and access score.task completion.SPSS analysis software was then used to analyze the behavioral data and students’ overall performance using the Pearson Productive Difference Correlation algorithm.Analyses are conducted to drill down into the data to derive a correlation between behavioral data and achievement.Then design a model for predicting grades based on decision tree algorithm and use the analysis of decision tree algorithm for student grade prediction to get the decision tree.The correlations between online learning characteristics of secondary school students are analyzed and validated for predicted performance.It is hoped that the research in this paper can expand the body of knowledge on data mining,decision tree algorithms and student learning behavior analysis.Finally,based on the data collected in the online learning platform,mining analysis and grade prediction are performed,and the results show that students’ online learning Behavior analysis ca n provide valuable suggestions for optimizing the teacher’s curriculum system and promoting the overall balanced development of students.