id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
fbem-12587	Niu, Qian; Ye, Xiaotong	Study of Bursary Grade Prediction Based on Integrated Learning	2023	4	.pdf	application/pdf	2731	102	47	Summary This paper centers on the grade prediction problem of college student grants, firstly, the dataset is imbalanced, then the original dataset is feature engineered to screen out the features that have an important influence on the prediction of grant grades, and finally, the Stacking integrated model is constructed with Random Forest, KNN, XGBoost, and CatBoost as the base learners, and the results show that the Stacking integrated model has a significant improvement in precision, recall , and F1-score in these evaluation criteria by comparing it with the other single models. For the training set data in each base learner, K-fold cross- validation is performed to obtain n feature matrices, and the information from these n matrices is merged to obtain the new training set data𝐷 ; While performing the cross-validation, the prediction of the test set is performed to get the K kinds of prediction data learned by a base learner, which is averaged as the final prediction result of the base learner on the test set.	cache/fbem-12587.pdf	txt/fbem-12587.txt