Use case · Energy & Utilities
Eneco: Next Best Action orchestration across every channel
Together with Eneco we built a Next Best Action framework that combines data, machine learning and marketing automation to decide the most relevant next step for every customer.
The challenge
The right message, channel and moment for each customer
Eneco wanted customer interactions to be more relevant, consistent and personal across all channels. That covered commercial communication, such as cross-sell and upsell, as well as service interactions.
The core question: how do you offer the right message, via the right channel, at the right moment, for each individual customer?
The solution
Every action backed by data, not gut feeling
Machine learning model
A Python model scores every possible action on the likelihood of a positive customer response.
Real-time orchestration
Integration with the Relay42 platform orchestrates customer interactions in real time.
Omnichannel delivery
Actions reach customers through the website and app, chat and telephony, and email and marketing campaigns.
Scoring card & dynamic queue
The action queue updates continuously based on context, response and behaviour.
The impact
A scalable, data-driven framework for customer interactions
Each interaction refines the next recommendation, so the framework keeps getting smarter.
- More relevant communication across every channel
- Higher product density through targeted cross-sell and upsell
- Richer customer profiles from service interactions
- Continuous learning as every interaction feeds the model
- Stronger customer relationships built on relevance
More use cases
See how other teams did it
Let’s talk
Ready for next-best-action marketing?
Tell us about your channels and customer data. We’ll show how an NBA framework could work for your organisation.