摘要
由一名新闻记者-机器人与机器学习每日新闻的工作人员新闻编辑-关于机器学习的最新研究结果已经发表。根据《中国人民日报》编辑对福建新闻的报道,研究表明:“学生的学习效果是评价教学质量的关键,在教学管理中起着重要作用。预测学生成绩是了解学生学习效果的一个重大挑战。”本报编辑引用了福建师范大学的一篇研究文章:“目前,许多研究都采用了机器学习方法,如决策树算法C4.5、ID3、CART、J48、随机森林等,但很少有研究探讨Bagging算法在这一领域的应用。”本文提出了一种基于Bagging-CART算法的学生成绩分类预测方法，首先对学生成绩数据进行预处理，然后利用Apriori方法挖掘强关联数据集，通过网格搜索确定最优超参数，并对Bagging-CART算法进行训练和预测，最后对CART、J48和Bagging-CART算法进行训练。结果表明,Bagging-CART模型的准确率为98.16%,召回率为91.80%,准确率为90.83%,F1得分为94.87%,与CART和J48相比,准确率、准确率和F1得分均高于CART和J48,召回率略低于CART 0.26%,"比J48高0.52%."
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Current study results on Machine Learning have be en published. According to news reporting originating from Fujian, People's Repu blic of China, by NewsRx editors, the research stated, "The learning effect of s tudents is crucial for assessing teaching quality, thus playing a significant ro le in teaching management. Predicting student achievement is a major challenge i n understanding the learning effect of students." Our news editors obtained a quote from the research from Fujian Normal Universit y, "Currently, many studies have utilized machine learning methods such as the d ecision tree algorithms C4.5, ID3, CART, J48, random forest, and others. However , few studies have explored the use of the Bagging algorithm in this field. Ther efore, this study proposes a classification prediction method for student achiev ement based on the Bagging-CART algorithm. Initially, the student achievement da ta is preprocessed, and the Apriori method is applied to mine the strongly assoc iated dataset. The optimal hyper-parameters are determined through grid search t o train and predict the Bagging-CART algorithm. Furthermore, the CART, J48, and Bagging-CART algorithms are trained, and their evaluation indicators are compare d using a confusion matrix. The results indicate that the Bagging-CART model ach ieves an accuracy of 98.16%, a recall rate of 91.80%, a precision of 90.83%, and an F1 score of 94.87%. In c omparison, the accuracy, precision, and F1 scores are higher than those obtained with CART and J48. Although the recall rate is slightly lower than that of CART by 0.26%, it is 0.52% higher than that of J48."
NETL
NSTL