This case study explains how we empowered Customer Support Agents with AI-based automation applied to phone and email cutomer service processes for one of the biggest Energy provider in Europe. Discover how machine learning (ML) models are increasing customer satisfaction and decreasing average handling time.
- Customer Analytics
- Customer Service
- Natural Language Processing
- Data Products
- Machine Learning
- Cloud
- Process Automation
- Energy Provider
Key challenges
Our client is one of the largest energy suppliers in Germany and Europe. They provide more than 5.5 million people with gas, power, water and energy-related services and products.
Operating in a highly homogenous market by nature, our client identified customer service quality as a key differentiator. In consequence, they started to and continue to increase customer support efficiency and quality by harnessing technology – especially AI – as a competitive advantage.
Our client was and is aiming at:
- Decreasing average handling time of customer requests;
- Increasing quality of customer interactions;
- Improving the understanding of customer needs and requests.
Our approach
We help our client to utilize AI in order to achieve their goals in three different ways:
Full process automation, building ML-based tooling to support the work of customer support agents and customer analytics.
- To automate email-based processes and build tools that support agents, we follow a rigorous process of thoroughly understanding the business processes, identifying use cases, validating and valuing their potential. Then, we take care of building and launching cloud-based Minimum Viable Products in the shortest time feasible. Finally, we continuously iterate to increase the performance with respect to clearly defined and measurable KPIs.
- In order to better understand their customers and automate phone-based processes, we help our client to build, improve, operate and maintain an intelligent system. It asks calling customers for the reason of their call, classifies as well as tracks the customer’s response. Based on the result, the system reacts by offering several self-services that either shorten the following interaction with a support agent or make the full interaction obsolete.
Benefits
- Automation of six phone-based processes within 15 months;
- Automation of three email-based processes in eight months;
- Two ready-to-use AI tools improving customer support agents performance in eleven months;
- Our client is immediately classifying 2.000.000 customer calls a year with regards to 50 different reasons. Therefore, the company saves nearly 1.8 Million minutes per year, representing approximately €900,000 in savings.
Technologies & Partners
Team involved
ML Engineers, Data Scientists, NLP Experts, Cloud Architects, DevOps Engineerq, and Project Managers collaborated with our client for 22 months on this project.
Discover what we can do for the Customer Service function and in the Data & Analytics expertise domain.
Thanks to our
Author
