Problem Statement

In the communication network system nowadays there is a lot of problem in managing the calls and keeping their track. The hackers are increased and there no system is generated to keep the track of these hackers and the system is required to detect the fraud in communication networks. Lots of customers are facing the problem of the less usage of their calls against paying high bills for not used calls. And Service providers are also not aware of these things that how to control the fraud in mobile communication network. There is need of the completely automated system that provides the solution for the fraud detection and manages the calls.

Mobile Fraud Detection System-The complete solution for the asset management.

What is Fraud Detection System?
Fraud in communications networks refers to the illegal access to the network and the use of its services. It is estimated that a mobile phone network operator may lose as much as million dollars a day due to fraudulent usage of mobile phones. The development of intelligent data analysis methods for fraud detection can be well motivated from an economic point of view. Additionally, the reputation of a network operator may suffer from an increasing number of fraud cases. .

Primary Goal:

1. Detects the possible frauds without straining the billing system.
2. Identifies fraudulent subscriber at an earlier stage using predefined fraudulent events.
3. Provision to categorize the subscribers as per customer groups.
4. Customer Group specific Parameterization.
5. Facility to check Roaming Subscription Fraud.
6. Call pattern matching.
7. Builds a firewall to prevent re-entry of fraudulent subscriber.
8. Facility to print the fraudulent list at the regular time intervals.
9. Alarm Generation
10. Customizable to handle different switch CDRs.
11. Archiving
12. Provision to Integrate with CRMT (Credit Risk Management Team)
13. Provision to Integrate with Prepaid Billing System (Hot Billing)
14. Provision to Integrate with Customer Care & Billing System
15. Provide event wise reports.
16. Easy-to-use user interface.

Development Phase 1 – Identification of possible fraud scenarios:
Following types of scenarios were identified in the trail conducted:
1. Usage Indicators (related to the way in which a mobile telephone is used).
2. Mobility Indicators (related to the mobility of the telephone).
3. Deductive Indicators (which arise as a by-product of fraudulent behavior e.g., overlapping calls and velocity checks)

The Zenwaves Network Security team proposes the following fraud combating methods in Mobile Fraud Detecting System:
1. Rule –based approach to fraud detection system.
2. Neutral network based approach to fraud detection system.
3. Grid –based Mobile phone fraud detection system.

Introduction to Mobile Fraud Detection System:
It is estimated that the mobile communications industry loses several million of hard dollars per year due to fraud. Therefore, prevention and early detection of fraudulent activity is an important goal for network operators. Certain types of commercial fraud are very hard to preclude by technical means. It is also anticipated that the introduction of new services can lead to the development of new ways to defraud the system. The use of sophisticated fraud detection techniques can assist in early detection of commercial frauds, and will also reduce the effect of technical frauds. Types of Analysis used for Fraud Detection: a) Absolute Analysis b) Differential Analysis

a) Absolute Analysis:
Existing fraud detection systems tend to interrogate sequences of Toll Tickets comparing a function of the various fields with fixed criteria known as triggers. A trigger, if activated, raises an alert status, which cumulatively would lead to an investigation by the network operator. Such fixed trigger systems perform what is known as an absolute analysis of the Toll Tickets and are good at detecting the extremes of fraudulent activity.

b) Differential Analysis:
In this type of analysis we monitor behavior of patterns of the mobile phone comparing its most recent activities with a history of its usage. Criteria can then be derived to use as triggers that are activated when usage patterns of the mobile phone change significantly over a short period of time.

Toll Ticket Data:
All the information that a fraud detection tool will need to handle is derived from the toll tickets provided by the network operator.
The following toll ticket components have been viewed to be the most fraud relevant measures:
1. Charged_IMSI (identifies the user)
2. First_Cell_Id (location characteristic for mobile originating calls)
3. Chargeable_Duration (base for all cost estimations)
4. B_Type_of_Number (for distinguishing between national / international calls)
5. Non_Charged_Party (the number dialled)

These components will continually be picked out of the toll tickets and incorporated into the user profiles in a cumulative manner. It is also anticipated that the analysis of cell congestion can provide useful ancillary information.

For further queries contact info@zenwaves.com