GLOBAL SYSTEM FOR MOBILE COMMUNICATION (GSM) SUBSCRIPTION FRAUD DETECTION SYSTEM USING ARTIFICIAL NEURAL NETWORK TECHNIQUE

GLOBAL SYSTEM FOR MOBILE COMMUNICATION (GSM) SUBSCRIPTION FRAUD DETECTION SYSTEM USING ARTIFICIAL NEURAL NETWORK TECHNIQUE
ABSTRACT
This project is concerned with GSM subscription fraud detection system using artificial neural network technique. Fraud is a multi-billion problem around the globe with huge loss of revenue. Fraud can affect the credibility and performance of telecommunication companies. The most difficult problem that faces the industry is the fact that fraud is dynamic, which means that whenever fraudsters feel that they will be detected, they device other ways to circumvent security measures. In such cases, the perpetrators intention is to completely avoid or at least reduce the charges for using the services. Subscription fraud is one of the major types of telecommunication fraud in which a customer obtain an account without intention to pay the bill. Thus at the level of a phone number, all transactions from the number will be fraudulent. In such cases abnormal usage occurs throughout the active period of the account; which is usually used for call selling or intensive self usage. This provides a means for illegal high profit business for fraudsters requiring minimal investment and relatively low risk of getting caught. A system to prevent subscription fraud in GSM telecommunications with high impact on long distance carriers is proposed to detect fraud. The system employs adaptive flexible techniques using advanced data analysis like Artificial Neural Networks (ANN). Fed with raw data, a neural network can quickly learn to pick up patterns of unusual variations that may suggest instances of fraud on a particular account. A total of 158 data samples were collected, trained and tested using a model that allows identifying potential fraudulent customers at the time of subscription. The result shows that 80% of the prediction accuracy has been obtained. From the result produced, artificial neural network has a potential to be used for detecting subscription fraud in telecommunication.
TABLE OF CONTETNS
Title Page – – – – – – – – – – i
Approval Page – – – – – – – – – ii
Dedication – – – – – – – – – – – iii
Acknowledgment – – – – – – – – – – – iv
Abstract – – – – – – – – – – – viii
Table of Contents — – – – – – – – – v
List of Figures – – – – – – – – – – x
CHAPTER ONE: INTRODUCTION
1.1 Background of the Study – – – – – – – 1
1.2 Statement of Problem- – – – – – – – 2
1.3 Objectives of the Study — – – – – – 2
1.4 Scope and Limitation of the Study – – – – – – – 3
1.5 Significance of the Study – – – – – – – 3
1.6 Definition of Terms – – – – – – – 4
CHAPTER TWO: LITERATURE REVIEW
2.1 Telecom Frauds – – – – – – – – 4
2. 1. 1 Subscription Fraud: – – – – – – – 7
2. 1. 2 Identity Theft: – – – – – – – – 7
2. 1.3 Roaming fraud: – – – – – – – – 8
2.1.4 DISA Fraud: – – – – – – – – 9
2. 1. 5 Phone Theft: – – – – – – – 10
2.1.6 Voicemail Fraud: – – – – – – – – 11
2. 1. 7 Some Factors Leading to Telecom Fraud – – – 11
2. 1. 8 Who Actually Commits Fraud- – – – – – – 12
2. 1. 9 Where do Fraudsters Work From – – – – – 13
2. 1. 10 Why do Fraudsters do it — – – – – – 12
2.2 Fraud Prevention and Detection – – – – – 12
2.2.1 Fraud Prevention – – – – – – – 17
2.2.2 Fraud Detection – – – – – – – – 20
2.2.2.1 Supervised Versus Unsupervised Learning – – – – 21
2.2.2.2 Supervised Methods of Fraud Detection – – – – 22
2.2.2.3 Unsupervised Methods of Fraud Detection- – – – 24
2.3 Fraud Detection Using Neural Network – – – – 25
2.4 GSM Subscription Fraud Detection Architectures – – – 27
2.4.1 System 1 Architecture – – – – – – – 27
2.4.1.1 Layer 1 – – – – – – – – – 28
2.4.1.2 Layer 2 – – – – – – – – – 28
2.4.1.3 Layer 3 – – – – – – – – – 28
2.4.2 System 2 – An ‘all in one’ Absolute Usage System – – – 28
2.4.3 System 3 – Introducing Diffential Usage – – – 29
CHAPTER THREE: SYSTEM ANALYSIS AND DESIGN
3.0 Analysis of the System – – – – – – – 31
3.1 Formulation of Model – – – – – – – 32
3.2 GSM Fraud Detection Using Neural Network- – – – 35
3.3 Object-Oriented Analysis of the System – – – – 38
3.4 Object-Oriented Design of the System – – – – – 39
3.4.1 Class Diagram of the System – – – – – – 40
3.4.2 Sequence Diagram of the System – – – – – 42
3.5 Database Design – – – – – – – – 46
3.5.1 Database diagram elements – – – – – – 46
3.6 Deployment diagram of the system – – – – – 47
CHAPTER FOUR: SYSTEM IMPLEMENTATION
4.0. Software Architecture – – – – – – – 49
4.1. System Requirements – – – – – – – 50
4.1.1 Hardware Requirements- – – – – – – – 50
4.1.2 Software Requirements – – – – – – – – 51
4.2. Development Environment, Coding and Testing Technique 51
4.3. Deployment Platform and Installation of the Software 53
4.4 Screen Shots of the Software Demos – – – – – – 53
4.5 User’s Guide – – – – – – 64
4.6 maintenance Guide – – – – – – 64
4.7 Program Documentation – – – – – – – – 65
CHAPTER FIVE: SUMMARY AND CONCLUSION
5.1 Summary – – – – – – – – – – 67
5.2 Conclusion – – – – – – – – – – 67
5.3 Recommendation – – – – – – – – – 68
5.4 Suggestion for further studies – – – – – – – 68
REFERENCE – – – – – – – – – 70
APPENDIX
Source Code
LIST OF FIGURES
Figure: 2.1 Flow of neutral network architecture 27
Figure: 2.2 An ‘all in one’ absolute usage system 29
Figure 2.3: Diffential usage system 30
Figure: 3.1 Architecture of the fraud detection tool 33
Figure 3.2 (a): Multilayer feed forward Neural network Architecture 36
Figure 3.2 (b): Back-propagation Neural network Architecture 38
Figure 3.3: Use Case boundary diagram of the system 39
Figure 3.4: Class diagram of the system 40
Figure 3.5 (a): Login sequence diagram 43
Figure 3.5(b): Make Call Sequence Diagram of the System 44
Figure 3.5 (c): End call Sequence Diagram of the System 45
Figure 3.5 (d): Check Detection Sequence Diagram of the System 45
Figure 3.6 Database Diagram of the System 47
Figure 3.7: Deployment Diagram of the System 48
Figure 4.1: The architecture of the software, GSM subscription fraud
detection using artificial neural network 49
Figure 4.2: Screen shot of the launch window 54
Figure 4.3 Screen shot of the welcome window 55
Figure 4.4: Screen shot of authenticate user window 56
Figure 4.4: Screen shot of make call window 57
Figure 4.6: Screen shot of timing window 58
Figure 4.7 Screen shot of call summary window 59
Figure 4.8 Screen shot of home page 60
Figure 4.9 Screen shot of add customer account detail page 61
Figure 4.10 Screen shot of check detection action 62
Figure 4.11 Screen shot of no detection page 63
Figure 4.12 Screen shot of fraud detections page