基于大数据决策树算法的学生成绩分析与预测模型仿真  

Analysis of student performance and simulation of prediction model based on big data decision tree algorithm

作　　者：吴晓倩[1] 权丽丽[1] 陈诚[1] 石磊[1] WU Xiaoqian;QUAN Lili;CHEN Cheng;SHI Lei(Anhui Medical College,Hefei 230061,China)

机构地区：[1]安徽医学高等专科学校,安徽合肥230061

出　　处：《电子设计工程》2020年第24期138-141,146,共5页Electronic Design Engineering

基　　金：2019年度安徽高校自然科学研究重点项目(KJ2019A1109)。

摘　　要：针对当前大学生成绩预测系统模型设计复杂、计算量大、预测准确性差、智能化程度低、受人为因素影响大等问题,提出了一种基于大数据决策树算法的学生成绩分析与预测模型。该模型将大学生成绩预测问题转换成大学生学习状态分类问题,以简化模型设计并提高大学生成绩预测的准确性;通过引入计算量较小的决策树算法,利用与成绩相关的数据实现对学生未来成绩的预测,从而提高成绩预测系统的智能性和客观性。该预测模型与传统的成绩预测方法相比,具有模型复杂度低、实现简单、智能化程度高、预测准确性及客观性强等优点。在实际成绩预测实验中,对学生成绩预测的准确率达到94%,证明了该预测模型的有效性。Aiming at the problems of current college student performance prediction system model design complexity,large amount of calculation,poor prediction accuracy,low intelligence,and great influence by human factors,this paper proposes a student performance analysis and prediction model based on big data decision tree algorithm.This model converts the problem of college student performance prediction into the classification of college student learning status to simplify model design and improve the accuracy of college student performance prediction;by introducing a decision tree algorithm with a small amount of calculation,the use of relevant data related to the performance to achieve future student performance Prediction,thereby improving the intelligence and objectivity of the performance prediction system.Compared with traditional performance prediction methods,this prediction model has the advantages of low model complexity,simple implementation,high degree of intelligence,strong prediction accuracy,and strong objectivity.In the actual performance prediction experiment of a class in a medical university,the accuracy of the design in predicting student performance reached 94%,which proved the validity of the design.

关 键 词：成绩预测 大数据 决策树 智能分析 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]