AI-Based Fraud Detection in MVNO Charging and Billing Systems

References

[1] F. Andriyanto and M. Suryanegara, “The QoE assessment model for 5G mobile technology,” in Proc. 2018 Int. Conf. Information Technology Systems and Innovation (ICITSI), 2018.

[2] F. Agboma and A. Liotta, “Quality of experience management in mobile content delivery systems,” Telecommunication Systems, vol. 37, pp. 197–207, 2008.

[3] S. Ulset, “Mobile virtual network operators: A strategic transaction cost analysis of preliminary experiences,” Telecommunications Policy, vol. 26, nos. 9–10, pp. 537–549, 2002.

[4] M. B. Krishna, “Mobile virtual network operators: A software defined mobile network perspective,” in Software Defined Mobile Networks (SDMN), 2015.

[5] M. Armbrust, A. Fox, R. Griffith, A. D. Joseph, R. Katz, A. Konwinski, G. Lee, D. Patterson, A. Rabkin, I. Stoica, and M. Zaharia, “A view of cloud computing,” Communications of the ACM, vol. 53, no. 4, pp. 50–58, 2010.

[6] 3GPP, “Telecommunication management; Charging management; Charging architecture and principles,” 3GPP TS 32.240, Release 16, 2021.

[7] 3GPP, “Telecommunication management; Charging management; Charging Data Record (CDR) parameter description,” 3GPP TS 32.298, Release 16, 2021.

[8] 3GPP, “Telecommunication management; Charging management; Diameter charging applications,” 3GPP TS 32.299, Release 16, 2021.

[9] 3GPP, “5G system; Charging service,” 3GPP TS 32.291, Release 17, 2022.

[10] 3GPP, “5G system; Charging management; 5G data connectivity charging,” 3GPP TS 32.255, Release 17, 2022.

[11] V. Vapnik, The Nature of Statistical Learning Theory, 2nd ed. New York, NY, USA: Springer, 2000.

[12] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.

[13] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273–297, 1995.

[14] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2016, pp. 785–794.

[15] F. T. Liu, K. M. Ting, and Z.-H. Zhou, “Isolation forest,” in Proc. 8th IEEE Int. Conf. Data Mining (ICDM), 2008, pp. 413–422.

[16] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.

[17] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. 3rd Int. Conf. Learning Representations (ICLR), 2015.

[18] A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd ed. Sebastopol, CA, USA: O’Reilly Media, 2019.

[19] A. B. Nassif, M. A. Talib, Q. Nasir, and F. M. Dakalbab, “Machine learning for anomaly detection: A systematic review,” IEEE Access, vol. 9, pp. 78658–78700, 2021.

[20] M. S. A. M. Al-Sharif, M. Al-Karaki, and others, “Fraud detection and management for telecommunication systems using artificial intelligence (AI),” in Proc. 2022 3rd Int. Conf. Smart Electronics and Communication (ICOSEC), 2022, pp. 1–6, doi: 10.1109/ICOSEC54921.2022.9951889.

@article{1723792,
      author = {Karthick Cherladine},
      title = {AI-Based Fraud Detection in MVNO Charging and Billing Systems},
      journal = {Iconic Research And Engineering Journals},
      year = {2022},
      volume = {5},
      number = {8},
      pages = {499-504},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1723792.pdf},
      abstract = {Mobile Virtual Network Operators (MVNOs) rely on complex charging and billing infrastructures to manage subscriber usage, service tariffs, roaming, and revenue generation. The increasing volume and complexity of 5G-enabled transactions create opportunities for fraudulent activities, including billing manipulation, subscription fraud, duplicate charging, abnormal usage, and unauthorized account activities. This paper proposes an Artificial Intelligence (AI)-based fraud detection framework for identifying suspicious transactions in MVNO charging and billing systems. The proposed approach integrates data preprocessing, feature engineering, supervised machine learning, and anomaly detection to distinguish legitimate and fraudulent activities. Machine learning models such as Random Forest, XGBoost, and Isolation Forest are considered for classification and behavioral anomaly detection. A fraud risk scoring mechanism is introduced to prioritize suspicious transactions and support timely intervention. The framework aims to improve fraud detection accuracy, reduce false-positive rates, and enable near-real-time monitoring. The proposed solution provides MVNOs with an intelligent and scalable approach for strengthening billing security and reducing financial losses.},
      keywords = {MVNO, Fraud Detection, Artificial Intelligence, Billing, Anomaly Detection, 5G.},
      month = {February},
      doi = {https://doi.org/10.64388/IREV5I8-1723792}
  }