Some elements of trade finance – such as checking the key documents underlying the trade – have been slow to digitalise. But that hasn’t prevented innovation: it’s facilitated it. Just ask ING Bank, says Conpend’s Founder Marc Smith and CEO Torben Sauer 

ING Bank has a strong reputation as a trade finance bank, as well as an innovator. Given this, it was a matter of time before the bank cracked one of the most intractable concerns preventing the full digitalisation of trade finance: the fact the documentary evidencing of the underlying trade (including bills of lading and letters of credit) remained paper based. Supply chains often involved countries and companies with sub-optimal connectivity that rely on paper-based documents being physically posted to the bank for manual checking. The checking is usually undertaken at a service centre, often in a third country: all of which generates delays as well as raises concerns over human errors and – in the worst-case scenarios – illegality.  

Attempts to digitalise the supply chain have been met with only partial success: there remaining a high percentage of trade-related documents that are printed originals requiring the human eye to ensure compliance (with all the imperfections and dangers this entails). Yet ING’s propensity for innovation has led them in a different direction. First, it accepted that electronic documentation is simply not viable for certain supply chains, which led it to focus instead on automating the process of checking the paper-based documents. 

Working with Conpend – a trade finance artificial intelligence (AI) automation specialist – ING deployed AI for the mundane aspects of documentary processing, which includes checking for compliance against International Chamber of Commerce (ICC) rules, as well as against anti-money laundering (AML) guidelines. A further check involved sanctions screening, including against America’s Office of Foreign Assets Control (OFAC) regulations. 

Integrating Conpend’s TRADE AI app, which automatically checks documents against inputted rules and regulations, the process has not only been made more efficient, it has freed up the operatives in the service centres to undertake the more meaningful work of checking the anomalies spotted by the app’s AI reading. 

The documents arrive by envelope and are scanned and securely sent to the operatives, who apply the TRADE AI app. The documents are scanned for key words and phrases against input rules and stipulations. If an anomaly is spotted, a query is raised and one of the operatives checks the document.  

The app has the power to convert all documents – whether they are copies, originals, clear or unclear papers – into machine readable words through optical character recognition. Yet the app is also self-learning from all previous transactions. Applying the learning to all future documents, the result is a process that is faster, more accurate and more precise than any human checkers can achieve – allowing it to produce analysis as well as recommend actions and solutions – all while constantly improving. 

Faster turnaround times, reduced errors and improved interaction with clients for day-to-day activities were ING’s aims, all achieved by the TRADE AI app that has now been adopted by the bank as part of their Digital Bank and Robotic Process Automation strategies. 

“The partnership has been a journey, and it has been approached as one right from the start, with no expectations that TRADE AI would be installed and immediately save time,” said Dermot Canavan, Trade Operations Manager at ING Bank. “That said, the app has delivered more than we expected quicker than we expected.” 

The partnership between Conpend and ING Bank – forged through the development of trade documentary checking – is now entrenched, opening up other bank processes that could benefit from AI.