Abstract: At present, with the rapid development of Internet technology and the arrival of the big data, experimental teaching methods based on big data platform have become more and more popular. Learning and using the massive data generated by the experimental teaching platform has become a hot issue in the field of education research and application. The analysis of student experimental behavior is conducted based on an online experimental teaching platform, which collects student experimental behavior data in real time, and uses the big data analysis technology to construct the student behavior portrait and quantitatively store the behavioralattributes of students. On the basis of behavior portrait, correlation algorithm and clustering algorithm are used to analyze students’ experimental behavior in single point and cluster, and realize visualized presentation. On the one hand, it provides scientific guidance for student management, on the other hand, it provides valuable decision-making information for the experimental teaching reform.