Banking on innovation: How ING uses generative AI to put people first

Every week, the global bank, ING, hears from 85,000 customers by phone and online chat in the Netherlands, one of its core markets. While 40 to 45 percent of those chats usually get resolved by the current classic chatbot, that still leaves another 16,500 customers a week needing to speak with a live agent for help. This can leave customers with potentially longer waiting times as they’re only able to get live help for non-urgent requests during working hours.

Generative AI’s ability to interact with human language in ways simply not possible before created an opportunity for teams from QuantumBlack, McKinsey's AI arm, and ING to explore how advanced chatbot technology could be used to improve the customer experience, giving customers the assistance they need immediately.

“There’s a huge challenge for the banking industry to improve the customer experience, but there’s also a huge amount of risk. You cannot just take technology coming out of a box to do this,” says McKinsey senior partner Andrea Del Miglio. “Leaders must ask themselves: What is the value you are adding to the technology? What is the edge you can add to this technology to make it more helpful for customers and better meet their needs?”

A joint ING and McKinsey team worked closely together for seven weeks to build a generative AI chatbot that offered customers immediate tailored help while maintaining clear guardrails to mitigate risk. The team started with an in-depth analysis of the existing chatbot to identify specific challenges. The final solution consisted of a multi-step pipeline to generate the best answer for the customer including knowledge retrieval from available data stores and a ranking of potential answers by helpfulness. In the case when several helpful answers arose, the system would offer multiple options to the customer – a process called disambiguation.

Lastly, before any answer was sent to the customer, a series of guardrails was applied. In order to do this, ING risk stakeholders were brought into this process from the very start and ING-specific guardrails (to avoid giving advice on mortgages and investment products, for example) were built using out-of-the-box tools from QuantumBlack Labs, our AI and machine learning innovation hub.

The gen AI chatbot was released on testing days to 10 percent of real customers in the Netherlands who were using the support chat function on the mobile app. It offered a customer experience that was demonstrably superior to the classic chatbot, providing customers with much more detailed and tailored responses, and helping them resolve their queries faster. Since launching in September 2023, thousands of customers have interacted with the new gen AI chatbot, making it the first-of-its-kind real-life customer-facing pilot conducted in Europe.

“By prioritizing real customer needs, security, and ease of use, ING was able to develop a bespoke customer support tool that gives users the best possible experience,” says ING chief operating officer Marnix van Stiphout.

The speed with which the chatbot was built and deployed far outpaced the timeline that’s been required to develop previous industry-standard chatbots, which can take several years of programming and finetuning to get right. What’s more, within the first seven weeks of use, the new chatbot was offering a better customer experience – helping 20 percent more customers avoid long wait times and offering instant gratification – compared to the previous solution. As the technology matures, more customers may switch from calling to chat, helping reduce the load on ING's call centers.

“When done right, using gen AI can be incredibly powerful in creating a better customer experience while also prioritizing the security of banking customers,” says McKinsey senior partner and co-leader of the Global Banking and Securities Practice Stephanie Hauser.

As part of a broader effort, ING focused on capability building across more than 50 support functions – in the Risk department, Contact Center department, and Analytics Office and Technology – giving ING a lighthouse case to more broadly scale their gen AI efforts.

Working together, the ING and McKinsey team created a path to double performance of the chatbot in the next six months, build a scalable model that can be extended to all other ING countries, and setup a technical foundation for ING to address a wide set of gen AI use-cases across the Group. The efforts helped define a blueprint to scale across ten markets with the potential to impact more than 37 million customers across 40 countries.

“This project has helped establish a solid technical foundation that puts ING at the forefront of gen AI applications within the banking industry,” says Bahadir Yilmaz, ING Chief Analytics Officer. “Gen AI technology will further evolve and we feel well-positioned to leverage those developments in order to offer the customer the best experience and remain a technology leader in our industry.”