SciELO - Scientific Electronic Library Online

vol.15 issue4  suppl.1Improving information exchange processes when implementing the State’s information function on the internal levelSecurity Risks in Web Penetration Testing 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


GARCIA NUNEZ, Alejandro  and  OLMEDO FLORES, Jorge Luis. High-availability distributed architecture for fraud detection. Rev cuba cienc informat [online]. 2021, vol.15, n.4, suppl.1, pp. 199-224.  Epub Dec 01, 2021. ISSN 2227-1899.

Early, fast and effective fraud detection in the telecommunications sector has become the spearhead for dealing with the most complex and diverse ways in which attacks and fraud can occur. Different techniques, tools and algorithms are used for detection, such as machine learning, which is a branch of Artificial Intelligence that allows computers to learn. In order to take full advantage of the benefits of machine learning, robust hardware and software architectures are set up. These are configured in a distributed manner allowing a set of computers to work as one in a transparent way, increasing performance and processing. The objective of this work is to develop a highly available distributed architecture using the Hortonworks data platform that allows the application of machine learning techniques in fraud detection. Apache components such as Spark, HBase and Hadoop were installed and configured to analyze traffic in large amounts of data. An example of the result of applying the K-means machine learning algorithm using the PySpark library for the creation of clusters is shown. The installation and configuration of the Hortonworks data platform resulted in an architecture that is highly available, flexible, scalable, fault tolerant and allows the use of machine learning for fraud detection.

Keywords : Fraud detection; Distributed Architecture; Machine learning.

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