Google Trying To Predict Flight Delays With Machine Learning

Flight delays are just the worst, especially during the holidays when everyone is in a rush. In an effort to try and at least make such incidents more bearable, Google is trying to predict whether flights are going to be delayed or not through its Flights app. This is being done via machine learning and taking historical data into account.

Normally, it would be next to impossible to predict if flights will be delayed or not. There are a variety of factors that are considered before flights are postponed, including weather, the conditions of the destination, and issues with the plane itself. Google seems to think, however, that past delays can allow machine learning to create a predictive model that users can base on, according to a blog post.

Using historic flight status data, our machine learning algorithms can predict some delays even when this information isn’t available from airlines yet—and delays are only flagged when we’re at least 80% confident in the prediction. We still recommend getting to the airport with enough time to spare, but hope this information can manage expectations and prevent surprises,” the post reads.

The new feature came with the new update to the travel app, Flights. Aside from the flight delay prediction, Google is also throwing in information on what “Basic Economy” flights are.

These details are some of the most important aspects to a flight that travelers take into consideration. As The Verge notes, airlines have been competing to offer the cheapest prices with every flight. In doing so, many of the amenities and services that used to be part of the package have been stripped, including baggage allowance or in-flight snacks.

Frequent flyers also need to know that their flights are going to take off on time, every time. Getting a heads up that they could be delayed can allow users to take precautions before getting to the airport.