End-to-end neural network architecture for fraud scoring in card payments

Jon Ander Gómez, Juan Arévalo, Roberto Paredes, Jordi Nin

Producció científica: Article en revista indexadaArticleAvaluat per experts

52 Cites (Scopus)


Millions of euros are lost every year due to fraudulent card transactions. The design and implementation of efficient fraud detection methods is mandatory to minimize such losses. In this paper, we present a neural network based system for fraud detection in banking systems. We use a real world dataset, and describe an end-to-end solution from the practitioner's perspective, by focusing on the following crucial aspects: unbalancedness, data processing and cost metric evaluation. Our analysis shows that the proposed solution achieves comparable performance values with state-of-the-art proprietary and costly solutions.

Idioma originalAnglès
Pàgines (de-a)175-181
Nombre de pàgines7
RevistaPattern Recognition Letters
Estat de la publicacióPublicada - 1 d’abr. 2018
Publicat externament


Navegar pels temes de recerca de 'End-to-end neural network architecture for fraud scoring in card payments'. Junts formen un fingerprint únic.

Com citar-ho