Citi, in partnership with advisory firm EY and analytics company SAS, has launched an artificial intelligence-based solution to digitise its trade compliance processes.

The NextGen project brings together EY’s business, risk and technology consulting experience in the financial services sector with SAS’ analytics platform to create a risk analytics scoring engine which can analyse large volumes of trade transactions.

The solution includes natural language processing to understand networks of related parties, unstructured data and customer activity over time, and process automation that combines analytic results and trade-related bank policies to help focus on trade transactions activities that may need further investigation.

“This real-time solution will help us to be able to more efficiently detect transactions with potential compliance concerns up front,” says Valeria Sica, global head of trade services for Citi’s treasury and trade solutions. “This solution assists in managing and comparing a large number of data points across current and prior transactions, which will provide more context and usable data to aid the decision maker in reviewing global trade transactions, which has traditionally been a very manual process across the industry.”

Many banks still rely on manual, paper-based processes, which drive up operational costs and impact the customer experience. Indeed, findings from a survey published in 2017 found that banks are squandering as much as £2.7bn each year because of outdated anti-money laundering (AML) systems – costs that could be saved by adopting machine learning and big data technology.

For John Ahearn, global head of trade for Citi treasury and trade solutions, this solution will go some way toward cutting compliance costs. “We process 9 million transactions annually, and the NextGen project will help us optimise our processes from the back office to the front, by expanding the use of digitisation, automation and advanced analytics,” he says.

Citi is not the first bank to digitise its compliance activities. In October last year, Commerzbank launched a pilot solution that will see it automate 80% of its “first line of defence” compliance checks of its trade finance processes by 2020.

Working with Conpend, a fintech firm that uses optical character recognition (OCR) and machine learning to digitise physical trade documents, recognise patterns and flag deviations, Commerzbank automated areas such as its anti-money laundering processes. Conpend also conducts automatic document checking and sanctions screening.