Deflecting 30% of routine customer service contacts

The Challenge

N26, the leading mobile bank in Europe with over $500M in funding, has seen tremendous growth to over two million customers in just a few years. The company operates across many different national markets in Europe, offering customer service in five languages, and plans to expand to the US.

To keep up with this strong growth, N26 faced the challenge of scaling customer service. N26 decided to investigate using AI to improve customer experience and operational efficiency, through faster responses to customer service chats.

N26 found existing cloud-based solutions weren’t able to fulfill its customization and data protection needs. In addition, the company wanted to automate complex, back-and-forth conversations.

The Solution

Using Rasa, N26 was able to get from idea to production in just four weeks. N26 deployed the assistant on their secure cloud environment with full data control.

A product team consisting of data scientists, designers, developers, and product managers, worked closely with customer service to identify the major use cases. Specifically, the team was able to handle more complex conversations using Rasa’s machine learning-based dialogue AI instead of hand-crafting each rule.

Now the AI assistant is running in five different languages in their mobile and web app, even handling complex tasks such as reports of credit cards being lost or stolen.

The Results

N26’s team was able to tweak the machine learning models to peak performance with their own data sets. Soon after going live in the mobile app, N26 quickly saw 20% of customer service requests handled by the AI assistant. N26 is working on bringing this to 30% and beyond.

With Rasa, we were able to scale our customer service and grow our user base significantly, and still provide the best customer experience. We further have more time to concentrate on the most important requests.

Gino Cordt, Chief Data Officer, N26