Location-aided fraud detection in banking operations

Fraud detection procedures for national and international economies have become quite important tasks. Ensuring the security of transactions carried out by banks and other financial institutions is one of the major factors affecting the reputation and profitability of such organizations. Public and private financial institutions establish organizational bodies responsible for carrying out controls for detecting and preventing fraudulent transactions. However, since people who perform fradulent transactions change their methods constantly in order not to get caught up, it gets more difficult to identify and detect this type of transactions. Detecting this type of transactions makes the support of technology compulsory, considering high volume and intensity of transactions. Among the applications that has been developed for the detection of fraudulent transactions, the prevalence of the rule-based systems are particularly noteworthy. As these systems may use of simple and compound rules, advanced data mapping technologies that make comparison in validated fraud databases, and other important databases mapping systems, they may be simple database systems that can detect suspicious behavior and directs this information to the right. However, we have not come across any model that takes into account of transaction location. The aim of this thesis study is to study the worth of location information of financial transactions for detecting the fraudulent transactions. The scope of work is to discover scenarios to detect fraudulent transactions by the support of geographic information systems with location, and time information and the help of models built by using data mining. Keywords: Fraudulent Transactions, Data Mining, Geographical Information Systems, Location Intelligence