Abstract:

Money laundering activity is one of the organized crimes in the world that causes a negative impact on the development of the national economy. Nowadays, it has become a global concern. Anti-Money laundering (AML) solutions facilitate to control it in a proper way. However, one of the fundamental challenges in AML solution is to identify real suspicious transactions. Illegal businesses use various kinds of money laundering techniques to induce their black money in the regular financial system to make it legitimate. To identify these suspicious transactions, various kinds of AML solutions have been introduced. Most of the AML solutions use pre-defined rules and statistical approaches to detect abnormal transactions activities based on customer transactions information.  The existing solutions help to detect the suspicious transactions. However, due to the fixed and predetermined rules, it is highly probable that a normal customer can be identified as a suspicious customer and the result would be increased in the false positive ratio. To overcome the above limitations, we propose a new dynamic approach to identifying suspicious customers in money transactions that are based on dynamic analysis of customer profile features to identify suspicious transactions. The experiment has been executed with real bank customers and their transactions data.  The experimental results provide promising outcomes in terms of accuracy.