Enhanced anomaly scores for isolation forests

作者：

Highlights：

• We propose novel anomaly scores for Isolation Forests.

• We design weighted variants of the anomaly score that embed additional information.

• We propose a novel aggregation function to combine the scores at forest level.

• Experiments confirm the suitability of the approach.

• The novel proposed scores outperform the original one.

摘要

•We propose novel anomaly scores for Isolation Forests.•We design weighted variants of the anomaly score that embed additional information.•We propose a novel aggregation function to combine the scores at forest level.•Experiments confirm the suitability of the approach.•The novel proposed scores outperform the original one.

论文关键词：Anomaly detection,Isolation forest,Anomaly score,Outliers

论文评审过程：Received 10 December 2020, Revised 25 May 2021, Accepted 14 June 2021, Available online 18 June 2021, Version of Record 1 July 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108115