Abstract
How to effectively mine students' behavior data is an important part of improving the level of university student information management. Aiming at the problems of imperfect student information management platform and low mining precision, this paper combines decision tree, neural network and naive Bayesian algorithm to establish a combined data mining model and a Spark-based university student behavior analysis and prediction platform. Campus behaviors such as regularity, living habits, and learning conditions are used as big data sources for predictive analysis and case verification. The results show that the prediction results of the model are consistent with the actual situation, and the average prediction error does not exceed 5%, which verifies the effectiveness of the method used. Teachers can analyze students' behavioral patterns according to their behavior characteristics and guide students' behaviors toward comprehensive health.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have