Detecting Telecommunication Fraud using Neural Networks through Data Mining

-Neural computing refers to a pattern recognition methodology for machine learning. The resulting model from neural computing is often called an artif icial neural network (ANN) or a neural network. Neural networks have been used in many business applications for pattern recognition, forecasting, prediction and classif ication. Neural network computing is a key component for any data mining tool kit. Applications of neural network based data mining tools are abound in f inance, marketing, manufacturing, information systems and so on. This essay discusses in detail the role of artif icial neural networks in prevention of telecommunication fraud. Keywords--Artif icial iintelligence, Artif icial neural networks (ANNs), Coral systems, Data Mining, Expert System, Falcon (Or Credit Card Issuers), Fraud Management Systems, Ghosting, Know ledge Base System, Rule Based System, Telecommunication fraud, Thresholding Systems. ——————————  —————————— 1 AN OVERVIEW OF TELECOMMUNICATION FRAUD HE telecommunication industry has expanded dramatically in the last few years with the development of affordable mobile phone technology (Pieprzyk J, Ghodosi H and Dawson E, 2007, pp 446-447). With the increasing number of mobile phone subscribers, global mobile phone fraud is also set to rise. It is a worldwide problem with substantial annual revenue losses of many companies. Telecommunication fraud which is the focus is appealing particularly to fraudsters as calling from the mobile terminal is not bound to a physical location and it is easy to get a subscription. This provides a means for illegal high profit business for fraudsters requiring minimal investment and relatively low risk of getting caught. Telecommunication fraud is defined as the unauthorized use, tampering or manipulation of a mobile phone or service. At the beginning of the twenty first century, the convergence of computing and communication technologies has altered considerably the way in which industrialized communities function. It has created unfold benefits for education, delivery of health services, recreation and commerce and changed considerably the nature of modern workplaces and patterns of employment. Telecommunication fraud can be simply described as any activity by which telecommunications service is obtained without intention of paying. This kind of fraud has certain characteristics that make it particularly attractive to fraudsters. The main one is that the danger of localization is small. This is because all actions are performed from a distance which in conjunction with the mess topology and the size of network makes the process of localization time consuming and expensive. Additionally no particularly sophisticated equipment is needed if one is needed at all. The simple knowledge of an access code, which can be acquired even with methods of social engineering, makes the implementation of fraud feasible. Finally the product of telecommunication fraud, a phone call is directly convertible to money. 2 TELECOMMUNICATION FRAUD DETECTION Fraud is a multi billions problem around the globe. The problem with telecommunication fraud is the huge loss of revenue and it can affect the credibility and performance of telecommunication companies. The most difficult problem that faces the industry is the fact that fraud is dynamic. This means that whenever fraudster’s feel that they will be detected they find other ways to circumvent security measures. Telecommunication fraud also involves the theft of services and deliberate abuse of voice and data networks. In such cases the perpetrator’s intention is to completely avoid or at least reduce the charges for using the services. Over the years, fraud has increased to the extent that losses to telephone companies are measured in terms of billions of American dollars. Fraud negatively impacts on the telephone company in 4 ways such as financially, marketing, customer relations and shareholder perceptions. There are various techniques available for managing and detecting telephone fraud these include: 1) Manual review of data, the problem with this technique is the fact that there are too many data records for a team to filter the fraudulent data. Typically a telecom company will have in order of 1 million or more records of telephone calls generated by their customers for a single month within a specific region. As a result this is a time consuming and laborious technique for detecting fraud. 2) Conventional analysis using a fixed rule based expert system together with statistical analysis. A rule based system is a set of rules that take into account the normal calling hours, the called destinations as well as the normal duration of the call and etc. 3) Adaptive flexible techniques using advanced data analysis like artificial neural networks (ANNs). Fed with T