According to ING, the EWS gathers and analyzes huge amounts of data to identify if clients are exposed to potential risks. Currently, the task is manually carried out by risk analysts, said Dutch banking major.
ING project leader Anand Autar said: “Speed is of the essence in credit risk management. The earlier we detect any risk, the quicker and better we can serve clients to prevent losses.
“Through machine learning, the EWS scans financial and non-financial information, such as news items from all over the world.”
ING claims that the EWS has a processing capacity of up to 80,000 articles every day. The AI-powered tool is ‘fed’ real-time market data sourced from Refinitiv (former Thomson Reuters) and news from public sources.
For articles published in regional media outlets, EWS uses the natural language processing and translation services of Google.
ING AI and Robotics head Görkem Köseoğlu said that the EWS learns from experience and in time is expected to do better in identifying the sentiment of news and developments in the market.
ING said that it will look to add predictive capabilities to the application in the near future.
Köseoğlu said: “This ambition requires further refinement of algorithms, and we’ll get there.
“Customers expect more predictive capabilities in their products and services, so for us meeting that customer demand is important.”
Earlier this month, ING through its corporate venture capital fund ING Ventures invested €1.3m alongside Unicredit in Italian fintech start-up Axyon AI to utilize AI technology for the syndicated loans market.
Axyon AI’s SynFinance is an AI-based platform that uses predictive analysis to identify investors who are most likely to participate in a syndicated loan.
In October, ING launched Katana Lens, an AI tool it had co-created with Dutch pension fund PGGM. Katana Lens has been designed to help investors find and compare interesting trade ideas.
