Hard to find new ways of money laundering
Suspected case information relies on manual summaries
Case investigation tasks are difficult to allocate reasonably
Currently, the anti-money laundering monitoring system adopted by banks mainly uses empirical rules as the main way to extract suspicious transactions against money laundering. Sinodata’s artificial smart anti-money laundering solution is based on supervised machine learning technology to risk score suspicious transactions, reduce the false alarm rate of suspicious transactions, and improve the reporting efficiency of suspicious transactions. Identify complex money laundering gangs that are not recognized by rules based on semi-supervised machine learning techniques to improve anti-money laundering technical capabilities.
Identify anti-money laundering gangs to expand suspicious account coverage
Optimize the review process
Optimize the existing empirical rule base
Optimize the investigator manpower and improve efficiency
Improving the case identification accuracy