The Application of Big Data Analytics Methods in Higher Education Management to the Design of Individualized Student Pathways

Abstract

The arrival of big data technology brings the possibility of realizing personalized education. This study applies big data analysis methods to students' personalized cultivation path, proposes a neurocognitive diagnosis method that integrates forgetting and knowledge point importance, and on this basis, constructs a personalized resource recommendation model based on cognitive diagnosis, which integrates convolutional neural network technology into the joint probability matrix decomposition model, and digs deeply into the information of personalized learning resources. Experiments show that the FAINCD cognitive diagnostic model in this paper shows better student performance prediction effect on different data sets, and its DOA value is above 0.85, which is significantly higher than that of the comparison method.The F-value of the CUPMF resource recommendation model is improved by 5.89%-11.89%, and the MAE value is decreased by 5.96%-14.84%, and the students' learning performance using this paper is improved by 15.81%, which is higher than that of the other methods. 15.81%, which is 2.56% to 5.29% higher than other methods. Therefore, the proposed model has a better effect of resource recommendation and learning facilitation, which can provide a guarantee for the personalized training of students.