A Semi-Supervised Approach to the Detection and Characterization of Outliers in Categorical Data

Abstract : In this paper we introduce a new approach of semi-supervised anomaly detection that deals with categorical data. Given a training set of instances (all belonging to the normal class), we analyze the relationships among features for the extraction of a discriminative characterization of the anomalous instances. Our key idea is to build a model characterizing the features of the normal instances and then use a set of distance-based techniques for the discrimination between the normal and the anomalous instances. We compare our approach with the state-of-the-art methods for semi-supervised anomaly detection. We empirically show that a specifically designed technique for the management of the categorical data outperforms the general-purpose approaches. We also show that, in contrast with other approaches that are opaque because their decision cannot be easily understood, our proposal produces a discriminative model that can be easily interpreted and used for the exploration of the data.
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-01275509
Contributor : Dino Ienco <>
Submitted on : Wednesday, February 17, 2016 - 3:36:43 PM
Last modification on : Wednesday, September 18, 2019 - 4:04:04 PM
Long-term archiving on : Wednesday, May 18, 2016 - 1:08:49 PM

File

tnnls.pdf
Files produced by the author(s)

Identifiers

Citation

Dino Ienco, Ruggero Pensa, Rosa Meo. A Semi-Supervised Approach to the Detection and Characterization of Outliers in Categorical Data. IEEE Transactions on Neural Networks and Learning Systems, IEEE, 2017, 28 (5), pp.1017-1029. ⟨10.1109/TNNLS.2016.2526063⟩. ⟨lirmm-01275509⟩

Share

Metrics

Record views

550

Files downloads

719