Low-cost airline Ryanair has revealed how it uses Amazon’s cloud-based artificial intelligence (AI) tools to predict which in-flight refreshments to stock to avoid disappointing its passengers.
The airline is known as a long-standing customer of Amazon Web Services (AWS), with the company’s public cloud technology being widely used in Ryanair’s operations, enabling it to reduce costs, reduce food waste and reduce carbon emissions. can reduce.
In addition, the company has now clarified how Amazon’s technology also helps the company make predictions and predictions about what food and drinks are likely to be in greatest demand on certain flights and on certain routes, so it can manage its inventory accordingly. To adjust.
“Your holiday starts on the plane,” said Aoife Greene, assistant assistant director and head of retail at Ryanair, whose job is to decide what refreshments to stock for each flight. “People want their gin and tonic. They want their panini with ham and cheese. They want to sit back and relax. They don’t want to hear, “No, that’s not available.” Our job is to make sure no one is disappointed.”
Previously, Greene’s team relied on written logs – which mapped out what refreshments were consumed or wasted on each trip – and their own observations to predict which items to stock up on, which is a significant undertaking given Ryanair operates 2,900 flights a day.
In addition, each aircraft has space for five refreshment carts that can only be filled once every 24 hours.
“I often joke that my colleagues who manage fuel consumption have an easy life,” says Greene. “They know where a particular plane is going, and they know how long it takes to get there. I don’t know if we’ll have 100 ballerinas or 100 rugby players on board.”
John Hurley, Ryanair
To help Greene and her team in their work, Ryanair is now using a machine learning tool — dubbed the “panini forecast” — that relies on the data it collects about what goods are bought and sold on board to help the airline. when planning what refreshments to stock. †
The forecasting tool uses an algorithm that combines data on what is sold and consumed during flights with information on journey length, time, season, departure location and destination, as well as passenger nationalities, to predict what will happen next. is probably in high demand for refreshments.
Ryanair chief technology officer John Hurley said the forecasting tool proved to be particularly useful in deciding which products to stock on newer routes, and had other benefits as well.
“Importantly, it has improved customer satisfaction, halved our waste and increased our sales,” said Hurley.
Now the company wants to apply the concept of the “panini predictor” to other parts of its business, so that it can, for example, take a more proactive and predictive approach to the maintenance of its aircraft and help it select the most fuel-efficient efficient aircraft to fly on certain routes.
“When AWS came on board, it lit up some sort of touch paper to get us started,” Hurley said. “We test these projects, analyze all this data, get the results back and for the most part just say ‘Wow’. It is a great opportunity to be even more future-oriented and efficient.”
Darren Hardman, vice president and general manager for the UK and Ireland at AWS, said the work the airline is doing “raises the bar” for what is possible in the global airline industry.
“Ryanair is driving innovation in the airline industry and is using AWS machine learning services to reinvent the way airlines deliver enhanced services to their customers, while increasing efficiency and improving the sustainability of their business,” he added.