NUST MISIS experts have created a smartphone app that lets you accurately predict flight delays. The estimates made by this app differ from the real values by only 12 minutes. This has been achieved using modern machine learning techniques.
Important factors affecting flight delays include weather conditions, airport congestion, traffic patterns and technical issues. To predict such events, neural networks based on machine learning methods are successfully used.
The application is based on a multilayer perceptron (MLP) model trained on one million flight records. This model can take into account the complex relationships between inputs and outputs. The algorithm uses various factors such as the time between arrival and departure, estimated time of arrival and departure at the airport, flight distance and weather conditions.
In the future, the app promises to be even more useful. The developers plan to improve its accuracy and optimize it to run on weaker mobile devices.
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.