| 用AUC评估分类器的预测性能 |
| |
| 引用本文： | 杨波,程泽凯,秦锋.用AUC评估分类器的预测性能[J].情报学报,2007(2):275-279. |
| |
| 作者姓名： | 杨波 程泽凯 秦锋 |
| |
| 作者单位： | 1. 安徽工业大学计算机学院,马鞍山,243002;通化师范学院计算机系,通化,134002
2. 安徽工业大学计算机学院,马鞍山,243002 |
| |
| 摘 要： | 准确率一直被作为分类器预测性能的主要评估标准,但是它存在着诸多的缺点和不足。本文将准确率与AUC(the area under the Receiver Operating Characteristic curve)进行了理论上的对比分析,并分别使用AUC和准确率对3种分类学习算法在15个两类数据集上进行了评估。综合理论和实验两个方面的结果,显示了AUC不但优于而且应该替代准确率,成为更好的分类器性能的评估度量。同时,用AUC对3种分类学习算法的重新评估,进一步证实了基于贝叶斯定理的NaiveBayes和TAN-CMI分类算法优于决策树分类算法C4．5。
|
| 关 键 词： | 准确率 交叉验证 |
| 修稿时间： | 2005年11月30 |
Using AUC to Evaluate Predictive Performance of Classifiers |
| |
| Yang Bo,Cheng Zekai,Qin Feng.Using AUC to Evaluate Predictive Performance of Classifiers[J].Journal of the China Society for Scientific andTechnical Information,2007(2):275-279. |
| |
| Authors: | Yang Bo Cheng Zekai Qin Feng |
| |
| Abstract: | Accuracy has been used as a main evaluation criterion for predictive performance of classifiers.However,it has many shortcomings and disadvantages.In this paper,we compared accuracy to AUC(the area under the Receiver Operating Characteristic curve)measure in theory and used respectively AUC and accuracy to evaluate three classification learning algorithms on fifteen binary datasets.Theoretical and experimental results show that AUC is not only a better measure than accuracy but also should replace it in comparing classifiers.Furthermore,using AUC to re-evaluate three classification algorithms shows classification algorithm NaiveBayes and TAN-CMI based on Bayes theorem are better than decision tree classification algorithm C4.5 in performance. |
| |
| Keywords: | ROC AUC |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
