Poor student identification method based on multi-classification BP-Adaboost

Abstract

The invention discloses a poor student identification method based on multi-classification BP-Adaboost, and the method comprises the following steps: (1) obtaining the multi-dimensional historical data of poor students in previous years, (2) carrying out the preprocessing of the collected historical data of poor students in previous years, and constructing a student feature matrix S; (3) dividingmulti-dimensional historical data of poor students in previous years into three categories according to the poor degree, marking student poor category labels, and constructing a training data set; (4)designing a BP-Adaboost classification model, and training the BP-Adaboost classification model by using the extracted data set constructed by the poverty student feature matrix of each poverty degree in previous years; and (5) training the model for auxiliary identification of poor students. A BP-Adaboost-based multi-classification model is designed by utilizing student behavior data generated by students in schools, and the model can quickly and accurately divide the students into three poverty categories so as to judge poverty conditions of the students and assist college poverty student management staff in making decisions.

Description

technical field [0001] The invention belongs to the technical field of feature extraction and classification algorithms, and in particular relates to a method for identifying poor students based on multi-classification BP-Adaboost. Background technique [0002] Student financial aid is an important content and an important measure for alleviating poverty, promoting educational equity, and realizing social equity. The identification of impoverished students in colleges and universities is the basic work for the effective implementation of the national student financial aid policy and an important part of promoting the precision of student financial aid. At present, the evaluation of poor students in most colleges and universities is made by the public selection of the class and the review of the department counselor after the township where the student is located shows the relevant certificate. This identification model has problems such as poverty identification bias, the s...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the difficulties in processing high-dimensional impoverished students’ data in the prior art and the difficulties in realizing precise subsidy for impoverished students, the present invention proposes a method for identifying impoverished students based on multi-classification BP-Adaboost

Images