As I discussed in the previous blog post in this series, the energy retail sector is facing a customer service crisis. The influence of challenger brands has created ever-increasing customer expectations for smarter, more personalised services. Meanwhile, tough macroeconomic conditions, exacerbated by the COVID-19 pandemic, are piling pressure on retailers to find new ways to help customers pay their bills and avoid falling into arrears.
In that previous piece, I hinted that the solution was a concept that SAS calls "intelligent decisioning." Today, I want to dive a little deeper into what intelligent decisioning is, and how it can help energy retailers weather the current storm and come out stronger on the other side.
To deliver the level of customer experience that today’s consumers expect and provide support and guidance to avoid nonpayment, you need to take a cross-channel, cross-functional approach. Each team within the business – marketing, installations, support, billing, collections and so on – must be able to understand its customer interactions in the context of both the current state of the customer relationship and the entire customer life cycle. That way, instead of acting in isolation, all your business functions can make consistent decisions based on a full understanding of customer lifetime value.
Intelligent decisioning
To achieve this kind of intelligent decisioning across hundreds of thousands of customer accounts, you can’t rely on manual analysis – you need to embed automated analytics into your business processes themselves. That’s going to mean moving beyond simplistic approaches based on applying various sets of business rules at a departmental level. It requires investment in more advanced analytics.
Moreover, to deliver successful, cost-effective intelligent decisioning, you need to be able to pick the right tool for each problem you’re trying to solve. Artificial intelligence and machine learning techniques should be part of your toolkit, as well as traditional statistical methods.
The best option is to create a single, central intelligent decisioning platform that gives you access to both traditional and AI-based modelling approaches, as well as powerful techniques such as constraint solving and optimisation. With a truly comprehensive analytics platform, your analysts and data scientists can always pick the right tool for the task at hand.
Managing the entire life cycle
It’s also vital to have an intelligent decisioning platform that manages and facilitates the entire analytics life cycle to help you get new tools and models into production – a key challenge for most energy retailers. Ideally, you want a single platform that guides you from data exploration, preparation and cleansing through model design, training and testing to deployment, monitoring, retraining and auditing. The platform should also offer a robust framework for data governance, decision auditing and explainability.
At SAS, we’re working with a host of energy companies around the world to transform customer service with intelligent decisioning. For example, we’ve helped Endesa adopt a strategic approach to customer segmentation, which delivers the customer insight to help define new products, formulate new customer acquisition strategies and reduce attrition. By embedding analysis of key customer attributes – such as environmental sensitivity, geographic location, customer lifetime value and propensity to churn – Endesa has been able to reduce customer attrition by 50% in just two years.
We can help you find the right path forward to embed intelligent decisioning into your business, understand customer behaviour and lifetime value, and make the right choices to transform the customer experience. You can find out more by downloading our paper on customer service and credit risk scoring in utilities here.
