An Empirical Comparison of Outlier Detection Algorithms
In recent years, researchers have proposed many different techniques for detecting outliers and other anomalies in data sets. In this paper we wish to examine a subset of these techniques, those that have been designed to discover outliers quickly. The algorithms in question are ORCA, LOADED, and RE...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Text |
| Language: | English |
| Subjects: | |
| Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.7648 http://www.cse.ohio-state.edu/dmrl/papers/kddws05.pdf |
| Summary: | In recent years, researchers have proposed many different techniques for detecting outliers and other anomalies in data sets. In this paper we wish to examine a subset of these techniques, those that have been designed to discover outliers quickly. The algorithms in question are ORCA, LOADED, and RELOADED. We have performed an empirical evaluation of these algorithms, and here present our results as guide to their strengths and weaknesses. 1. |
|---|