Open AccessStudy on Prediction of Course Failure Based on Improved Bagging-C4.5 Algorithm
Author(s) -
Jiebo Luo
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1861/1/012013
Subject(s) - course (navigation) , computer science , feature (linguistics) , set (abstract data type) , machine learning , algorithm , test set , test (biology) , warning system , artificial intelligence , data mining , engineering , biology , programming language , aerospace engineering , paleontology , telecommunications , philosophy , linguistics
At present, the research of academic early warning system needs to know the situation of course failing. There are many research methods of course failing, but there are defects of low accuracy and long prediction time. In order to improve the accuracy and accuracy of course failing prediction, the improved Bagging-C4.5 algorithm is designed to predict the course failing. Firstly, the research progress of current social talent demand and course failure prediction is analyzed, then the test data set is determined, and the feature combination with the most influence is selected as the feature set of course failure prediction. Finally, the improved Bagging-C4.5 algorithm is used to realize the failure prediction, and the comparison test is conducted with other algorithms. The results show that the algorithm in this paper has high accuracy and accuracy in predicting course failure.