We introduce a semi-supervised active learning system for fraud detection; we select a semi-supervised approach due to the fact that typical available datasets are totally unlabeled or only partially labeled, moreover the active learning methodology allows us to obtain very good results by requiring a lower number of labels with respect to traditional approaches.

A Semi-supervised Active Learning System for Fraud Detection

DI BLASI, Gianpiero;MEO, Rosa;PENSA, Ruggero Gaetano
2013

Abstract

We introduce a semi-supervised active learning system for fraud detection; we select a semi-supervised approach due to the fact that typical available datasets are totally unlabeled or only partially labeled, moreover the active learning methodology allows us to obtain very good results by requiring a lower number of labels with respect to traditional approaches.
0.9
DIPARTIMENTO DI INFORMATICA, Università di Torino
http://www.di.unito.it/~meo/
fraud detection; anomaly detection; Outliers detection; active learning; semi-supervised learning
G. Di Blasi; R. Meo; S. Cavalli; R.G. Pensa
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2318/140623
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact