Chapter

Database Systems for Advanced Applications

Volume 5982 of the series Lecture Notes in Computer Science pp 396-399

Visual Evaluation of Outlier Detection Models

  • Elke AchtertAffiliated withInstitut für Informatik, Ludwig-Maximilians-Universität München
  • , Hans-Peter KriegelAffiliated withInstitut für Informatik, Ludwig-Maximilians-Universität München
  • , Lisa ReichertAffiliated withInstitut für Informatik, Ludwig-Maximilians-Universität München
  • , Erich SchubertAffiliated withInstitut für Informatik, Ludwig-Maximilians-Universität München
  • , Remigius WojdanowskiAffiliated withInstitut für Informatik, Ludwig-Maximilians-Universität München
  • , Arthur ZimekAffiliated withInstitut für Informatik, Ludwig-Maximilians-Universität München

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Many outlier detection methods do not merely provide the decision for a single data object being or not being an outlier. Instead, many approaches give an “outlier score” or “outlier factor” indicating “how much” the respective data object is an outlier. Such outlier scores differ widely in their range, contrast, and expressiveness between different outlier models. Even for one and the same outlier model, the same score can indicate a different degree of “outlierness” in different data sets or regions of different characteristics in one data set. Here, we demonstrate a visualization tool based on a unification of outlier scores that allows to compare and evaluate outlier scores visually even for high dimensional data.