A two-phase approach for unexpected pattern mining

作者：

Highlights：

• A new mining task, unexpected pattern retrieval is proposed.

• Frequent pattern mining algorithms on the multi-dimensional dataset is extended.

• The partial results among the subgroups are shared.

• New index is built to retrieval unexpected patterns interactively.

• Experiments show the efficiency and effectiveness of the proposed method.

摘要

•A new mining task, unexpected pattern retrieval is proposed.•Frequent pattern mining algorithms on the multi-dimensional dataset is extended.•The partial results among the subgroups are shared.•New index is built to retrieval unexpected patterns interactively.•Experiments show the efficiency and effectiveness of the proposed method.

论文关键词：Frequent pattern mining,Subgroup discovery,Multi-dimensional dataset,Data mining,Anomaly detection

论文评审过程：Received 28 May 2019, Revised 9 September 2019, Accepted 9 September 2019, Available online 10 September 2019, Version of Record 18 September 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112946