Telecom traffic pumping analytics via explainable data science

作者:

Highlights:

• We propose a novel approach for dealing with traffic pumping.

• We tailor a machine learning approach for fraud prediction in telecom.

• We use an unsupervised learning perspective in the context of XAI.

• Successful business case: all the lawsuits filed were confirmed to be fraudulent.

摘要

Traffic pumping is a type of fraud committed in several countries, in which small telephone operators inflate the number of incoming calls to their networks, profiting from a higher access charge in relation to the network operator associated with the origin of the call. The identification of traffic pumping is complex due to the lack of labels for performing supervised learning, and the scarce literature on the topic. We propose a decision support system for fraud detection via clustering and decision trees. After data collection and feature engineering, we group the potential fraud cases into various clusters via an unsupervised learning approach. Then, we constructed a decision tree by using the cluster memberships as labels, evolving into the rules of a given variable and a certain label required for filing lawsuits against the suspicious cases. Telecommunication experts validate these rules to seek a legal resource against alleged perpetrators. We present the results of a case study from a Chilean telecommunication provider. All the lawsuits taken by the legal department were granted, confirming our success in dramatically reducing current and future fraud losses for the company.

论文关键词:Fraud prediction,Unsupervised learning,Interpretable machine learning,EXplainable AI (XAI),Telecommunications

论文评审过程:Received 30 July 2020, Revised 5 March 2021, Accepted 16 March 2021, Available online 24 March 2021, Version of Record 24 September 2021.

论文官网地址:https://doi.org/10.1016/j.dss.2021.113559