Research and construction of student management platform for special needs students with decision tree model and big data technology
Jingkun Jin · Systems and Soft Computing · 2025
This study focuses on enhancing the intelligence and operational efficiency of student management platforms. Given the critical role of data-driven decision-making in promoting educational quality improvement, the research deeply integrates decision tree models with big data processing technologies such as Hadoop and Spark to optimize student management strategies. Through improvements to the decision tree model, the accuracy of student behavior prediction has significantly increased from the original 78% to 92%, greatly enhancing predictive accuracy. Additionally, leveraging big data technology allows for real-time data updates and analysis, significantly shortening data processing time, ensuring that the effective insights needed for management decisions can be provided promptly. Furthermore, the platform innovatively constructs an intelligent early warning system that can keenly capture potential learning issues among students and intervene in a timely manner; the personalized learning recommendation system tailors course plans based on student behavior patterns and preferences, effectively improving learning efficiency. The results of this research fully demonstrate the significant value of incorporating advanced data processing technologies into student management platforms, laying a solid foundation for building intelligent education systems. It illustrates how data-driven decision-making aids in achieving personalized and equitable education, showcasing the tremendous transformative potential of educational informationization.