Roaming Fraud Detection via Busy Rate Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting roaming fraud in mobile communication networks have a low positive detection rate, leading to significant financial losses as they fail to effectively identify and prevent fraudulent activities, particularly due to the lack of real-time signaling connections to the home network for SIM cards maintaining permanent connections abroad.
Innovation Solution
The method involves analyzing the 'busy rate' of suspicious SIM cards using PING calls within the SS7/ISUP protocol simulator, allowing for timely counter-measures such as barring or disconnection of SIM cards that exceed a threshold duration of busy status, thereby reducing damage by up to 95%.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If MEGS filter criteria are applied to detect roaming fraud, then the detection coverage is increased, but the false alarm rate increases significantly
Solution Approach 1:
The detection process is segmented into multiple stages: initial MEGS filtering, followed by selective PING call verification only for suspicious cases. This segmentation allows broad coverage while maintaining precision by applying intensive verification only where needed.
Solution Approach 2:
A protocol simulator acting as an intermediary is introduced between the MEGS detection system and the home network. This intermediary performs PING calls to verify suspicious SIM cards without requiring actual signaling connections to the home network, thus reducing false alarms while maintaining detection accuracy.
2Measurement precision
If real-time signaling connections to home network are established for all roaming SIM cards, then fraud detection accuracy is improved, but the network load and complexity increase
Solution Approach 1:
The network verification process is segmented to apply real-time checking only to suspicious SIM cards identified by MEGS, rather than all roaming SIM cards. This reduces network signaling complexity while maintaining detection accuracy for fraudulent cases.
Solution Approach 2:
Instead of establishing actual signaling connections to the home network, a protocol simulator creates a virtual copy of the home network environment. This allows verification of SIM card status without the complexity of real network connections, while still achieving accurate fraud detection.
3Measurement precision
If PING calls are performed for all MEGS alerts, then the detection accuracy is improved, but the processing time and resource consumption increase
Solution Approach 1:
The verification process is segmented to perform PING calls only on a subset of MEGS alerts that meet specific suspicion criteria. This selective approach maintains high detection accuracy while significantly reducing processing time and resource consumption compared to verifying all alerts.
Solution Approach 2:
Instead of performing complete verification on all MEGS alerts, the system applies partial verification (PING calls) only to the most suspicious cases. This partial action approach achieves sufficient detection accuracy while minimizing time and resource investment.
Data Source
AI summary
The invention relates to a method for fraud recognition in mobile communication networks, in particular, for fraud recognition in the case of roaming connections, wherein a roaming connection provided for a user identity module, a SIM, is checked for possible misuse by means of at least one criterion. According to the invention, the “engaged rate” for the relevant user identity model is checked as an essential criterion for a given period.