A comparative evaluation of novelty detection algorithms for discrete sequences

Domingues, Rémi; Michiardi, Pietro; Barlet, Jérémie; Filippone, Maurizio
Artificial Intelligence Review journal, 8 November 2019, Springer

The identi cation of anomalies in temporal data is a core component of numerous research areas such as intrusion detection, fault prevention, genomics and fraud detection. This article provides an experimental comparison of candidate methods for the novelty detection problem applied to discrete sequences. The objective of this study is to identify which state-of-the-art methods are efficient and appropriate candidates for a given use case. These recommendations rely on extensive novelty detection experiments based on a variety of public datasets in addition to novel industrial datasets. We also perform thorough scalability and memory usage tests resulting in new supplementary insights of the methods' performance, key selection criteria to solve problems relying on large volumes of data and to meet the expectations of applications subject to strict response time constraints.

Data Science
Eurecom Ref:
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in Artificial Intelligence Review journal, 8 November 2019, Springer and is available at : http://doi.org/10.1007/s10462-019-09779-4

PERMALINK : https://www.eurecom.fr/publication/5829