Class-Based Outlier Detection: Staying Zombies or Awaiting for Resurrection?

• Type: Article in International Conference Proceedings Book
• Date: 2015

Authors

Leona Nezvalová (Author) Other; Lubos Popelínsky (Author) Other; Luis Torgo (Author) FCUP; Karel Vaculík (Author) Other

Conference proceedings International

Title: Advances in Intelligent Data Analysis XIV

Pages: 193-204

14th International Symposium on Intelligent Data Analysis (IDA)

Saint Etienne, FRANCE, OCT 22-24, 2015

Indexing

ISI Web of Knowledge - 1 Citation

Scopus - 1 Citation

Other information

Authenticus ID: P-00G-SZE

DOI: 10.1007/978-3-319-24465-5_17

Abstract (EN): This paper addresses the task of finding outliers within each class in the context of supervised classification problems. Class-based outliers are cases that deviate too much with respect to the cases of the same class. We introduce a novel method for outlier detection in labelled data based on Random Forests and compare it with existing methods both on artificial and real-world data. We show that it is competitive with the existing methods and sometimes gives more intuitive results. We also provide an overview for outlier detection in labelled data. The main contribution are two methods for class-based outlier description and interpretation.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 12