图 书 馆
类关联规则的总体覆盖率如何影响分类器的准确性？How overall coverage of class association rules affects the accuracy of the classifier? |
|
| 课程网址: | http://videolectures.net/sikdd2019_mattiev_class_association/ |
| 主讲教师: | Jamolbek Mattiev |
| 开课单位: | 普里莫尔斯卡大学数学、自然科学和信息技术学院 |
| 开课时间: | 2019-11-14 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Associative classification (AC) is a data mining approach that combines classification and association rule mining to build classification models (classifiers). Experimental results show that in average the CBA-based approaches could achieve higher accuracy than some of the traditional classification methods. In this paper, we focus on associative classification, where class association rules are generated and analyzed to build a simple, compact, understandable and relatively accurate classifier. Furthermore, we discuss how overall coverage and average rule coverage of such classifiers affect their classification accuracy. We compare our method that uses constrained exhaustive search with some “classical” classification rule learning algorithm that uses greedy heuristic search on accuracy in some “real-life” datasets. We have performed experiments on 11 datasets from UCI Machine Learning Database Repository. Experimental evaluation shows that with decreasing overall coverage our proposed method tends to get slightly worse classification accuracy than the “classical” classification rule learning algorithms. Otherwise, the accuracy is similar or on some datasets even better than Naive Bayes and C4.5. On the other hand, the average rule coverage of our proposed method seems to have no effect on classification accuracy. |
| 关 键 词: | 普里莫尔斯卡大学; 数据挖掘; 自然科学和信息技术学院 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-09-14：cyh |
| 最后编审: | 2022-09-19：cyh |
| 阅读次数: | 36 |