Improving electric fraud detection using class imbalance strategies

Mat́ias Di Martino, Federico Decia, Juan Molinelli, Alicia Ferńandez

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

70 Citas (Scopus)

Resumen

Improving nontechnical loss detection is a huge challenge for electric companies. The great number of clients and the diversity of the different types of fraud makes this a very complex task. In this paper we present a fraud detection strategy based on class imbalance research. An automatic detection tool combining classification strategies is proposed. Individual classifiers such as One Class SVM, Cost Sensitive SVM (CS-SVM), Optimum Path Forest (OPF) and C4.5 Tree, and combination functions are designed taken special care in the data's class imbalance nature. Analysis over consumers historical kWh load profile data from Uruguayan Electric Company (UTE) shows that using combination and balancing techniques improves automatic detection performance.

Idioma originalInglés
Título de la publicación alojadaICPRAM 2012 - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods
Páginas135-141
Número de páginas7
EstadoPublicada - 2012
Publicado de forma externa
Evento1st International Conference on Pattern Recognition Applications and Methods, ICPRAM 2012 - Vilamoura, Algarve
Duración: 6 feb. 20128 feb. 2012

Serie de la publicación

NombreICPRAM 2012 - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods
Volumen2

Conferencia

Conferencia1st International Conference on Pattern Recognition Applications and Methods, ICPRAM 2012
País/TerritorioPortugal
CiudadVilamoura, Algarve
Período6/02/128/02/12

Huella

Profundice en los temas de investigación de 'Improving electric fraud detection using class imbalance strategies'. En conjunto forman una huella única.

Citar esto