Study of Bursary Grade Prediction Based on Integrated Learning

Abstract

With the advancement of digital campus, many scholars have addressed the problems of low efficiency of financial aid work in colleges and universities and insufficient fairness and impartiality of the evaluation process, and proposed the solution of using big data and machine learning algorithms to identify the students who are really in need of help and realise the fairness of bursary awarding. Firstly, multi-dimensional feature vectors are constructed by processing and analysing students' daily behavioural data, then Multi-SMOTE oversampling technology is used to solve the problem of balancing classification samples in the process of bursary evaluation, and then Stacking model fusion algorithms are used to integrate multiple classifiers in order to improve the prediction accuracy. The experimental results prove that the method is significantly better than a single classification model in terms of precision and recall, which can improve the efficiency of college financial aid work, as well as ensure the fairness and accuracy of the financial aid process and provide better financial aid services for students.