SciELO - Scientific Electronic Library Online

vol.15 issue4  suppl.1Security Risks in Web Penetration TestingArchitecture for the detection of security policy violations author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand



  • Have no cited articlesCited by SciELO

Related links

  • Have no similar articlesSimilars in SciELO


Revista Cubana de Ciencias Informáticas

On-line version ISSN 2227-1899


AMEIJEIRAS SANCHEZ, David; VALDES SUAREZ, Odeynis  and  GONZALEZ DIEZ, Héctor. Anomaly detection algorithms with deep networks. Review for Bank Fraud Detection. Rev cuba cienc informat [online]. 2021, vol.15, n.4, suppl.1, pp. 244-264.  Epub Dec 01, 2021. ISSN 2227-1899.

The various advances in science and the large volumes of data that have been generated only in recent years have surpassed the human capacity to collect, store and understand them without the use of the appropriate tools, limiting the fraud detection capabilities of companies. institutions. One form of bank fraud is that which occurs with credit / debit cards; these have become a very popular payment method for online purchases and services. It is for these reasons that an analysis of the main anomaly detection algorithms based on deep learning focused on bank fraud was carried out. Architectures based on AEs were found to excel at unsupervised tasks and (Long short-term memory) LSTMs for classification tasks.

Keywords : anomaly detection; bank fraud; deep learning; credit cards.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )