6431

Histogram-based Outlier Score (HBOS): A fast Unsupervised Anomaly Detection Algorithm

Markus Goldstein, Andreas Dengel

KI-2012: Poster and Demo Track German Conference on Artificial Intelligence (KI-2012), 35th, September 24-27, Saarbr├╝cken, Germany , Pages: 59-63 , Online , 2012
Unsupervised anomaly detection is the process of finding outliers in data sets without prior training. In this paper, a histogram-based outlier detection (HBOS) algorithm is presented, which scores records in linear time. It assumes independence of the features making it much faster than multivariate approaches at the cost of less precision. A comparative evaluation on three UCI data sets and 10 standard algorithms show, that it can detect global outliers as reliable as state-of-the-art algorithms, but it performs poor on local outlier problems. HBOS is in our experiments up to 5 times faster than clustering based algorithms and up to 7 times faster than nearest-neighbor based methods.

Show BibTex:

@inproceedings {
       abstract = {Unsupervised anomaly detection is the process of finding outliers in data sets without prior training. In this paper, a histogram-based outlier detection (HBOS) algorithm is presented, which scores records in linear time. It assumes independence of the features making it much faster than multivariate approaches at the cost of less precision. A comparative evaluation on three UCI data sets and 10 standard algorithms show, that it can detect global outliers as reliable as state-of-the-art algorithms, but it performs poor on local outlier problems. HBOS is in our experiments up to 5 times faster than clustering based algorithms and up to 7 times faster than nearest-neighbor based methods.},
       number = {}, 
       month = {9}, 
       year = {2012}, 
       title = {Histogram-based Outlier Score (HBOS): A fast Unsupervised Anomaly Detection Algorithm}, 
       journal = {}, 
       volume = {}, 
       pages = {59-63}, 
       publisher = {Online}, 
       author = {Markus Goldstein, Andreas Dengel}, 
       keywords = {Outlier Detection, Anomaly Detection, Histogram-based scoring, Big Data},
       url = {http://www.dfki.de/web/forschung/publikationen/renameFileForDownload?filename=HBOS-KI-2012.pdf&file_id=uploads_1716, http://www.dfki.de/KI2012/PosterDemoTrack/, http://www.dfki.de/web/forschung/publikationen/renameFileForDownload?filename=HBOS-poster.pdf&file_id=uploads_1717}
}