4.5 Article

Weighted frequent sequential pattern mining

期刊

APPLIED INTELLIGENCE
卷 52, 期 1, 页码 254-281

出版社

SPRINGER
DOI: 10.1007/s10489-021-02290-w

关键词

Data mining; Pattern mining; Sequence mining; Weighted sequence

向作者/读者索取更多资源

Data mining is the study of extracting useful information from massive amounts of data, with sequential pattern mining being a major branch. Weighted sequential pattern mining is more feasible in today's datasets due to items having different importance in real-life scenarios. This research introduces a new pruning technique and framework to generate a small number of candidate sequences faster without compromising completeness, significantly outperforming other existing approaches.
Trillions of bytes of data are generated every day in different forms, and extracting useful information from that massive amount of data is the study of data mining. Sequential pattern mining is a major branch of data mining that deals with mining frequent sequential patterns from sequence databases. Due to items having different importance in real-life scenarios, they cannot be treated uniformly. With today's datasets, the use of weights in sequential pattern mining is much more feasible. In most cases, as in real-life datasets, pushing weights will give a better understanding of the dataset, as it will also measure the importance of an item inside a pattern rather than treating all the items equally. Many techniques have been introduced to mine weighted sequential patterns, but typically these algorithms generate a massive number of candidate patterns and take a long time to execute. This work aims to introduce a new pruning technique and a complete framework that takes much less time and generates a small number of candidate sequences without compromising with completeness. Performance evaluation on real-life datasets shows that our proposed approach can mine weighted patterns substantially faster than other existing approaches.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据