Machine Learning and Artificial Intelligence methods and techniques to combat fraud in Telecommunications
Data mining techniques applied to fraud management
Keywords:
machine learning; telecommunication fraud; bypass fraud; artificial intelligence; data miningAbstract
The present work includes a bibliographical study on different methods and techniques of Data Mining (MD), Machine Learning (ML) and Artificial Intelligence (AI), associated with the fight against fraud in telecommunications, which is in constant transformation and has been as the services and technologies become more complex, the amount of data to be processed is increasing, which leads to an increase in the response time to fraud if appropriate techniques are not used, in addition to requiring the combination of various data sources, so this type of tool is essential, both for the detection of patterns (fraud behaviors) and for the automation of work processes that allow reducing response times to it, this is achieved with the application of a series of methods that can be supervised, semi-supervised and unsupervised that comprise a series of algorithms for the treatment of large volumes of data, and specifically for bypass fraud treatment. By reducing fraud detection and mitigation time, as well as the correct characterization of fraudulent behavior patterns, income assurance is guaranteed and economic losses are avoided.
References
Abdallah, A., M. A. Maarof & A. Zainal (2016). "Fraud detection system: A survey". Journal of Network and Computer Applications, 68: 90-113.
Al Bougha, M. R. (2016). "Comparing data mining classification algorithms in detection of simbox fraud".
Alcívar León, C. R. (2020). "Diseño de un modelo predictivo a través de la técnica de minera de datos ‘Random Forest’para la detección de fraude bypass en redes telefónicas en el Ecuador".
Arana Porlles, D. A. (2017). "Influencia de un sistema integrado de información en la gestión del fraude en una empresa de telecomunicaciones, 2016".
Arias, F. & N. Cerpa (2008). "Extendiendo el modelo e-SCARF de detección de fraude en sistemas de comercio electrónico". Ingeniare. Revista chilena de ingeniería, 16(2): 282-294.
Arun, K., M. Ali, G. Irtaza & T. Anwar (2020). "Big Data analytics with Machine Learning for iot sensed data". Pal Arch's, Journal of Archaeology of Egypt/Egyptology 17(7): 5293-5301.
Association, C. F. C. (2021). Fraud loss survey report, 2021.
Cano Cancela, J. R. I., David; Moreno Izquierdo, Raúl (2011). Improving Fraud Detection Modeling.
Castro Aguilar, G. F. (2017). "Modelo para el aseguramiento de ingresos en organizaciones orientadas a proyectos basado en minería de datos anómalos".
Chouiekh, A. & E. H. I. E. Haj (2018). "Convnets for fraud detection analysis". Procedia Computer Science, 127: 133-138.
Da Costa, R. F. L. (2020). "Next Generation Machine Learning Based Real Time Fraud Detection".
Eng, D. A. & S. G. G. Álvarez (2018). "Lógica Difusa para la detección de comportamientos anómalos en los sistemas de telefonía". Tono, Revista Técnica de la Empresa de Telecomunicaciones de Cuba S.A., 14(2): 73-84.
Ferreira, L., A. Pilastri, C. Martins, P. Santos & P. Cortez (2020). "An automated and distributed Machine Learning framework for telecommunications risk management".
Getahun, A. (2020). Telecom Voice Traffic Termination Fraud Detection Using Ensemble Learning: The Case of Ethio Telecom, St. Mary’s University.
Ighneiwa, I. & H. Mohamed (2017). "Bypass fraud detection: Artificial intelligence approach". arXiv preprint arXiv:1711.04627.
Jiménez Burgos, M. L. "El impacto del fraude en empresas de telecomunicaciones".
Kouam, A. J., A. C. Viana & A. Tchana (2021). "SIMBox bypass frauds in cellular networks: Strategies, evolution, detection, and future directions". IEEE Communications Surveys & Tutorials.
Menes Camejo, I., G. Arcos Medina & K. Gallegos Carrillo (2015). "Desempeño de algoritmos de minería en indicadores académicos: Árbol de Decisión y Regresión Logística". Revista Cubana de Ciencias Informáticas, 9(4): 104-117.
Orbe Ordoñez, M. A. (2018). Propuesta metodológica de analítica de datos para estudio y análisis de tráfico en redes de telecomunicaciones, Quito, 2017.
Pérez, A. M., et al. (2004). "Aplicaciones de aprendizaje no supervisado para la detección de patrones de fraude en telecomunicaciones". Comunicaciones de Telefónica I+D, (34): 161-180.
Subudhi, S. & S. Panigrahi (2016). "Use of fuzzy clustering and support vector machine for detecting fraud in mobile telecommunication networks". International Journal of Security and Networks, 11(1-2): 3-11.
Tarmazakov, E. I. & D. S. Silnov (2018). Modern approaches to prevent fraud in mobile communications networks. IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), IEEE.
Zhao, Q., K. Chen, T. Li, Y. Yang & X. Wang (2018). "Detecting telecommunication fraud by understanding the contents of a call". Cybersecurity, 1(1): 1-12.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Claudia Beatríz Martínez Castro, Jose Alberto Vilalta Alonso
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.