How artificial intelligence is helping one bank handle millions of critical alerts every month
High-volume administrative tasks are a feature of every business. Time-consuming and labour-intensive, they take employees away from activities where they could be adding more value. Artificial Intelligence and Machine Learning can help businesses complete these tasks more efficiently – faster, with less errors and at less cost – and often with a positive impact on customer experience.
Our client was acutely aware of these issues. This bank was using a team of human reviewers to check more than 100,000 ‘sanctions alerts’ every day. The alerts, generated by the bank’s sanction screening systems, trigger on transactions that might involve sanctioned parties and/or jurisdictions. Despite the bank’s best efforts to refine their systems, more than 95% of the alerts ended up being classified by reviewers as false positives.
We developed a tool, using a supervised Machine Learning algorithm, to help with the task. The tool is capable of processing one million alerts per minute, a task that would take a team of human reviewers over a month. Our client is now using the tool to reduce reliance on human reviewers and has realised a 50% reduction in processing costs as a result.
Download this case story to find out:
© 2020 KPMG LLP a UK limited liability partnership and a member firm of the KPMG global organisation of independent member firms affiliated with KPMG International Limited, a private English company limited by guarantee. All rights reserved.
For more detail about the structure of the KPMG global organisation please visit https://home.kpmg/governance.