Ryanair taps up AWS machine learning tech to manage in-flight refreshment stocks

Ryanair’s low-cost airline has revealed how it is using Amazon’s cloud-based artificial intelligence (AI) tools to forecast what in-flight refreshments it should stock to avoid disappointing its passengers.

The airline is known to be a long-term Amazon Web Services (AWS) customer, with the firm’s public cloud technology in widespread use across Ryanair’s operations, enabling it to lower costs, reduce food waste and cut its carbon emissions.

In addition, the firm has now lifted the lid on how Amazon’s technology is also helping it to forecast and make predictions about what food and beverages are likely to be in highest demand during certain flights and on particular routes so it can adjust its inventory accordingly.

“Your holiday starts on the aircraft,” said Aoife Greene, Ryanair’s deputy director ancillary and head of retail, whose job it is to decide what refreshments each flight should stock. “People want their gin and tonic. They want their ham and cheese panini. They want to sit back and relax. They do not want to hear, ‘No, that’s not available’. It’s our job to make sure no one is disappointed. ”

Previously, Greene’s team relied on written logs – charting what refreshments had been consumed or wasted during each journey – and their own observations to forecast what items to stock, which is a significant undertaking given that Ryanair operates 2,900 flights a day.

In addition to this, each plane has space for five refreshment trolleys that can only be stocked once every 24 hours.

“I often joke that my colleagues who manage fuel consumption have an easy life,” said Greene. “They know where a particular plane is going, and they know how long it will take to get there. I have no way of knowing whether we’re going to have 100 ballerinas or 100 rugby players on board. ”

“When AWS came on board, it sort of let the touch paper get us going. We’re testing these projects, analyzing all this data, getting the results back, and, for the most part, just saying, ‘Wow’ ”

John Hurley, Ryanair

To assist Greene and her team in their work, Ryanair is now using a machine learning tool – dubbed the “panini predictor” – that relies on the data collected about what goods are bought and sold on board to help the airline plan what refreshments to stock .

The predictor tool uses an algorithm that combines data about what’s been sold and consumed during flights with information about the length of the journey, the time of day, season, departure location and destination, as well as the nationalities of the passengers, to predict what refreshments are likely to be in high demand.

Ryanair chief technology officer John Hurley said the predictor tool was proving to be particularly useful when deciding what products to stock on newer routes, and had brought about other benefits too.

“Importantly, it’s improved customer satisfaction, cut our waste in half, and boosted our sales,” said Hurley.

Now the company is looking to apply the concept of the “panini predictor” to other parts of its business, so it can take a more proactive and predictive approach to the maintenance of its aircraft, for example, and help it select the most fuel- efficient aircraft to run on certain routes.

“When AWS came on board, it sort of let the touch paper get us going,” said Hurley. We’re testing these projects, analyzing all this data, getting the results back, and, for the most part, just saying, ‘Wow’. It’s a major opportunity to be even more future-focused and efficient. ”

Darren Hardman, vice-president and general manager for UK and Ireland at AWS, said the airline’s work is doing is “raising the bar” for what is possible in the global air travel industry.

“Ryanair is driving innovation in the aviation industry and utilizing AWS machine learning services to reinvent the way airlines deliver enhanced services to their customers while deriving increased efficiencies and improving sustainability across their business,” he added.

Leave a Comment

Your email address will not be published.