Educational data mining for student performance prediction in artificial intelligence environment

In education, with the application of these information technologies, massive student data continue to produce, in order to realize the processing of data information, the traditional data mining technology is applied to the mass of education data processing process derived from a new technology, that is, education data mining technology. Among them, student performance prediction is an important application direction in education data mining, can help teachers to optimise their teaching decisions and help students to improve their learning plans. However, as of now, most of the models for student performance prediction suffer from weak generalization ability and poor feature correlation. Therefore, this paper proposes a student performance prediction method based on feature selection and Bagging integrated learning, which analyzes the model and a single prediction model, effectively solves the problem of low prediction accuracy of a single model, and improves the ability of the model to deal with the unseen examples to a certain extent, with a strong generalization ability.