FOUNDATION FRAMEWORK to understand future passenger volumes and plan accordingly, resulting in better service for passengers and a much more efficient operation.”
We asked Andrew Isenman, Head of Technology, Cloud and Data at Heathrow, further questions to find out more.
What were the key factors that led Heathrow to choose the Databricks Data Intelligence Platform to unify and govern your data and AI initiatives?
Heathrow is the largest airport in Europe; we welcome over 82 million passengers and handle over 460,000 flights annually. Naturally, our operations generate a high volume of data, and we rely on over 26TB of it – including passenger numbers, flights, airlines, seasonal performance, traffic and weather patterns – to make critical real-time decisions.
Maximising the value of our data is critical to our continued success, and we wanted to build upon our forecasting capabilities by refining our approach to data and AI. As such, we decided to partner with Databricks.
Could you elaborate on the specific challenges you faced prior to using Databricks and how the platform addressed them?
We initially had a suite of legacy data tools in place, which scattered and siloed our data. This approach was slowing processes and productivity, increasing costs and compromising on accuracy. Without distributed computational power and a highperforming data platform, our forecasting model required two weeks and two people to manage.
To overcome our challenges, we needed a data intelligence platform and decided to centralise our data and analytics on the Databricks Data Intelligence Platform on Microsoft Azure. A year on, we’ ve drastically modernised our forecasting model, reduced errors and costs, and gained insights for AI expansion.
How is Databricks’ Unity Catalog helping Heathrow ensure secure and consistent data usage across the airport?
Maximising the value of our data whilst maintaining security has always been a priority. As part of our partnership with Databricks, we decided to implement data governance with its Unity Catalog solution to secure our data and AI assets under a single permission model. By doing so, we’ re furthering safe and consistent data use across Heathrow.
With the ability to plan predictive maintenance and optimise service interruptions with the new forecasting model, how has this impacted cost savings and traveller experience during peak travel periods?
It’ s important to first note that airport customer satisfaction is directly impacted by passenger wait times. In fact, if a passenger is in line for longer than five minutes, we consider it a breach of customer experience. So, by leveraging Databricks’ solutions, we’ ve been able to improve customer satisfaction by optimising passenger flow within varying areas. For instance, we’ ve sped forecast insights from two weeks to four hours while decreasing the margin of error from 30 % to 10 %. Moreover, our advanced forecasting capabilities now mean we can prepare our teams for peak travel periods so they can proactively respond with efficient passenger flow, thus putting customer satisfaction at the forefront.
How has integrating Power BI with Databricks improved decisionmaking processes at Heathrow?
Evolving our decision-making capabilities required cross-team collaboration. As such, we integrated Power BI to ingest data from the lakehouse into dashboards and visualisations for business reporting – thereby furthering safe and collaborative data use across Heathrow.
As you look toward establishing a centre of excellence for data and AI, how do you envision Heathrow’ s use of MLflow and Databricks Delta Sharing evolving to support better collaboration with airlines, ground handlers and other partners?
By implementing model tracking and data sharing, we’ ll be able to gain a more in-depth understanding of future passenger volumes and potential service interruptions. That way, we can plan accordingly and ensure Heathrow customers always receive excellent service. We’ ll also have the ability to further strengthen our forecasting capabilities to enhance our operations and improve airport efficiency. �
Andrew Isenman, Head of Technology, Cloud and Data at Heathrow
www. intelligentbuild. tech 19