AI programs allow the company to better predict how many booked passengers will actually board a flight. This allows the exact number of meals required to be calculated and KLM achieves up to 63% less food waste depending on the expected number of passengers per flight. Annually, this represents a saving of more than 100,000 kilos of food.
“Investments in digital technology are a priority for KLM. The application of artificial intelligence contributes enormously to improving our air operations and making them more sustainable. The fight against food waste is a good example of this, as tens of thousands of fewer meals are thrown away on our flights every year,” said Marjan Rintel, CEO of KLM.
KLM is working on using artificial intelligence to determine the number of meals on board and help combat food waste. Not all bookings made result in a passenger on board a KLM aircraft. Depending on the class, between 3 and 5% of booked passengers do not show up (on time) for the flight.
The latest Artificial Intelligence model (TRAYS) is the first developed specifically for KLM's catering activities. The model predicts the number of passengers on board based on historical data. The Meals on Board System (MOBS) receives the expected number of passengers per flight with separate forecasts for Business, Premium Comfort and Economy classes.
Prediction using the AI model begins 17 days before departure and continues up to 20 minutes before flight departure. This means that the most accurate possible number of passengers is predicted throughout the catering process, from purchasing to loading, thus avoiding over-meals.
The TRAYS AI model was launched late last year by Kickstart AI. The initiative brought together talent from leading companies, including KLM, bol, Ahold Delhaize, NS and ING, to work on the development of this model.
“We are pleased to have been able to make a valuable contribution to this important project for KLM. Our goal with Kickstart AI is to accelerate the adoption of AI in the Dutch business community and we look forward to working closely with Dutch companies to make this happen,” said Sander Stomph, CEO and co-founder of Kickstart AI.
A three-month analysis shows that 63% less food is wasted compared to catering for each passenger booked. The biggest improvement can be seen on KLM's intercontinental flights from Schiphol, where 2.5 fewer meals (1.3 kg) have to be thrown away per flight. Annually, this is equivalent to a saving of 111,000 kilos of food on all KLM flights that have service from the airport.
KLM is also working on applying artificial intelligence in other parts of its business operations. For example, AI is important in making aircraft maintenance smarter. Additionally, AI programs are used to simulate expected bad weather days, making it clear in advance what schedule would be best to allow flights to continue as much as possible. AI also helps customers by providing them with personalized travel advice after booking a flight.