SOREX: subspace outlier ranking exploration toolkit

摘要: Outlier mining is an important data analysis task to distinguish exceptional outliers from regular objects. In recent research novel outlier ranking methods propose focus on hidden in subspace projections of the data. However, focusing only detection these approaches miss provide reasons why object should be considered as outlier. In this work, we a toolkit for exploration rankings. To enable and complete knowledge extraction further descriptive information addition pure outliers. As wittinesses outlierness object, about relevant describing properties. We provided SOREX open source framework our website it easily extensible suitable educational purposes emerging area.