Fighting Economical Crime
Solution for Anti-Money Laundering
Problem
The Legislator obliges financial institutions to trace transactions and detect suspicious ones and report them to the Chief Inspector of Financial Information (CIFI).
Normal methods applied in systems today are based on traditional SQL queries that operate within limits of earlier defined rules or parameters. They are not able to adjust to changeable patterns or schemes of "money laundering" without considerable changse to the program or support from an expert in this field.
Banks are processing million of transactions and have thousands or millions of customers. Systems that are based on pre-defined rules do not allow them to be flexible in chasing ever changing ways of "money laundering" and creativity in economical crime.
Solution
Saragosta offers FinDet as the solution to detect suspicious transaction to extend the portfolio of existing methods with a technology based on data mining and artificial intelligence.
We apply data mining processes to detect and analyze huge quantities of data that is divided into a couple of steps.
First, data is integrated in order to form one format.
The second step is visualization, conjunction, and interpretation of obvious and hidden connections, complicated relations, and patterns of activities included in data.
The last step is getting results that need to be acceptable and understandable for the final user.
The Data Mining Module is based on the GhostMiner application and is composed of two parts: Developer and Analyzer.
Developer is used to automatically create classification rules and to detect suspicious transactions based on models prepared in the training set of given transactions.
Analyzer is used as a tool to detect suspicious transactions from among all transactions delivered by the system. Results of an analysis are demonstrated in a special summary report.
The application of the Data Mining Module allows the detection of suspicious transactions in an automatic and more accurate manner. It requires to create own training set of transactions that defines classes of transactions. Such a set may be created in two ways:
Training transactions may be delivered from the register of suspicious transactions.
Training transactions may be also initially prepared due to the existence of the data clusterization module.
The algorithms applied in the GhostMiner package are based on the most modern methods of neural networks, decision trees, and visualization.