A Supervised Machine Learning Approach for Telecom Fraud Detection Using IPDR Data

DOI

10.2991/978-94-6239-697-5_6How to use a DOI?

Keywords

Machine Learning; Artificial Intelligence; Fraud Detection; Anomaly Detection; Tele communication Networks; Internet Protocol Detail Record (IPDR)

Abstract

With the increasing development of the telecommunication networks, the Internet Protocol Detail Records (IPDRs) have grown exponentially, and the detection of the fraud and anomalies has become more and more complicated. The conventional rule-based systems are not effective to identify changing and nuanced trends of fraud. In this paper, a supervised machine learning-based telecom fraud detection framework is presented using a synthetic IPDR dataset. A two-stage classification procedure is applied, binary classification is considered to detect the fraudulent sessions, and then multiclass classification is applied to establish the type of fraud. The models such as Support Vector Machine (SVM), Random Forest and XGBoost are trained on leak-free, session-based behavioral features. The models address class imbalance by employing weighted learning methods. Accuracy, precision, recall and F1-score are used to assess model performance. The experimental findings suggest that the best overall accuracy of an algorithm is that of the Random Forest, the most likely to be accurate in subtle and low-frequency fraud categories is SVM, and the overall performance of XGBoost is balanced across all the classes. The results prove that supervised learning is effective in detecting IPDR-based telecom fraud and that the selection of the model depends on the nature of the frauds.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Divya Sharma
AU  - Satnam Kaur
AU  - Mamta Dabra
AU  - Divya Bansal
PY  - 2026
DA  - 2026/06/04
TI  - A Supervised Machine Learning Approach for Telecom Fraud Detection Using IPDR Data
BT  - Proceedings of the Conference on Bridging Engineering Disciplines with AI and Machine Learning (BEDAIML 2026)
PB  - Atlantis Press
SP  - 49
EP  - 59
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-697-5_6
DO  - 10.2991/978-94-6239-697-5_6
ID  - Sharma2026
ER  -