Local projections for high-dimensional outlier detection

By Thomas Ortner, Peter Filzmoser, Maia Rohm, Sarka Brodinova, and Christian Breiteneder

Abstract

A novel approach for outlier detection is proposed, called local projections, which is based on concepts of the Local Outlier Factor (LOF) (Breunig et al. in Lof: identifying densitybased local outliers. In: ACM sigmod record, ACM, volume 29, pp. 93-104, 2000) and ROBPCA (Hubert et al. in Technometrics 47(1):64-79, 2005). By using aspects of both methods, this algorithm is robust towards noise variables and is capable of performing outlier detection in multi-group situations. The idea is to focus on local descriptions of the observations and their neighbors using linear projections. The outlyingness of an observation is determined by a weighted distance of the observation to all identified projection spaces, with weights depending on the appropriateness of the local description. Experiments with simulated and real data demonstrate the usefulness of this method when compared to existing outlier detection algorithms.

Reference

T. Ortner, P. Filzmoser, M. Rohm, S. Brodinova, C. Breiteneder: "Local projections for high-dimensional outlier detection"; METRON, 1 (2021), 79; 18 pages.

BibTeX

@article{TUW-293128,     author = {Ortner, Thomas and Filzmoser, Peter and Rohm, Maia and Brodinova, Sarka and Breiteneder, Christian},     title = {Local projections for high-dimensional outlier detection},     journal = {METRON},     year = {2021},     volume = {1},     number = {79},     numpages = {18},     url = {https://link.springer.com/article/10.1007/s40300-020-00183-5},     doi = {10.1007/s40300-020-00183-5} } Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.