Over the last year, EDF has undergone a huge transformation that has seen large investments into its retail customers business and business-wide innovation that has elevated performance across multiple units. The judges were impressed with the collaborative efforts, team cohesion, and demonstrable productivity because of EDF’s efforts and investment.
With a £20 million transformation programme, EDF has been able to overhaul its processes by moving from a fully centralised process to a hybrid federated approach. What was once a data and AI capability solely supporting the EDF retail business evolved within one year, with today’s capabilities extending into business and wholesale, with nuclear on the roadmap. None of this would have been possible without a fully cohesive data and analytics team.
Under the mission to help Britain achieve net zero emissions, EDF has leveraged data to be the main tool to address this aim. The transformation achievements have included:
- Transitioning to a cloud native data platform, retiring legacy systems, and saving £3 million annually.
- The safe migration of 5.5 million accounts.
- Debt analytics leading to over £55 million in payment resolutions and support for financially vulnerable customers.
- Data science contributing to a four-fold increase in ML products.
- Billing to settlements process reconciling approximately £75 million in value.
- Integration of marketing tools, resulting in 30% increase in net zero product sales and handling 71% of SMART meter bookings.
EDF’s platform became an enterprise product, which meant the team needed to drive value outside of retail. EDF manages around £10 billion-worth of energy every year and with new MHHS regulations requiring half-hourly energy settlement a requirement, EDF’s data team decided to use this regulatory demand to its advantage and use the MHHS to improve volume forecasting data product which forecasts and hedges energy positions on the market.
After ingestion, advanced ML models must be built to provide forecasts and short-term forecasts need to run every half an hour, managing significant financial risk (approximately £300 million). These forecasts run over enormous datasets:
- Consumption data from smart and non-smart meters totalling 613 billion rows annually.
- Met Office half-hourly forecasts.
- Industry consumption data across 5.5 million accounts.
- Account forecast models for the year – covering win, retention, and churn.
This was further complemented by EDF’s centre of excellence which provides organisation-wide empowerment through the new federated approach. It was important to address risks and difficulties such as consistent onboarding of users regardless of tool, framework competency, communication, access to correct tooling, and more.
The EDF data and tech graduate scheme has become a gamechanger for the data team, delivering a consistent pipeline of talent and new ideas. With placements in four different disciplines, graduates gain exposure to diverse data fields. The scheme is supported by a competency framework and aligned pay and benefits; EDF provides a structured career path for personal growth and retention. At the time of submission, EDF had 22 current data placements and 14 graduates securing their first data roles.
EDF are part of the DataIQ membership programme – the trusted global collaboration and intelligence platform for data leaders. Find out more here: https://www.dataiq.global/membership/
