基于数据挖掘的学业成绩分析与预测研究
Research on Academic Performance Prediction Based on Data Mining
叶伊 1许新华 1陈苏娜 1陶胜阳1
作者信息
- 1. 湖北师范大学 计算机与信息工程学院,湖北 黄石 435000
- 折叠
摘要
利用大量教育数据进行分析是当前教育领域研究的热潮,但从海量的数据中提取关键信息进行分析,分析的结果却往往差强人意.文章主要利用Pycharm对学生数据进行可视化与数据挖掘分析,从学生基本情况、学习困难度、学生时间分配、学业成绩四个维度进行相关性分析,确定成绩预测模型的指标,利用BP神经网络算法构建成绩预测模型,通过Matlab进行实验与仿真,实现成绩分级预测,利用MSE进行预测模型评估,实验结果表明该模型预测能力与稳定性较好,具有一定的效用.
Abstract
The use of a large number of educational data for analysis is a hot trend in the field of education research,but the key information extracted from the massive data for analysis,the analysis results are often unsatisfactory.This paper mainly uses Pycharm to visualization and data mining analysis of student data,conducts correlation analysis from four dimensions of students'basic situation,learning difficulty,student time allocation and academic achievement,determines the indicators of the achievement prediction model,constructs the achievement prediction model using BP neural network algorithm,and conducts experiments and simulation through Matlab.The prediction model is evaluated by MSE.The experimental results show that the prediction ability and stability of the model are good,and it has certain utility.
关键词
数据挖掘/成绩预测/BP神经网络Key words
data mining/performance prediction/BP neural network引用本文复制引用
基金项目
湖北师范大学2022年度研究生科研创新项目(20220550)
出版年
2024
NETL
NSTL
维普
万方数据