Google Cloud wants banks to embrace artificial intelligence for flagging fraud.  

The company just released a new tool that does away with rules-based systems for AML compliance in favor of an AI-generated risk score based on a bank’s historical data.  

In a typical system, 95% of alerts for review turn out to be “false positives,” which waste time and resources for compliance teams. Google’s tool cuts down on the overall number of alerts that need human review, without letting risk management wane, thus increasing operational efficiency and effectiveness, according to the company.  

Since HSBC became an early tester of the product (it began using it in 2019), the tech has cut down the bank’s number of alerts by as much as 60%. It also now detects two to four times more “true positive” risk, or confirmed suspicious activity, Google said.  

By integrating Google’s tool into its customer monitoring framework, HSBC has been able to “improve the precision of our financial crime detection and reduce alert volumes, meaning less investigation time is spent chasing false leads,” according to head of compliance Jennifer Calvery. “We have also reduced the processing time required to analyze billions of transactions across millions of accounts from several weeks to a few days.”