Have you ever planned to travel by air, got to the airport early enough, only to discover minutes to departure time that your flight had been delayed or cancelled? If you’re a Nigerian and you have travelled by Arik Air, it’s a frequent thing. But guess what, Google has developed a fantastic algorithm to help you avoid this sort of situation.
Google has updated its Google Flights feature with a machine learning algorithm that hopes to accurately predict if your upcoming flight will be delayed.
Google Flights is an online flight booking search service which facilitates the purchase of airline tickets through third party suppliers. It has been around for a while now (not globally though), but this new feature is sure to send it to the prime-time.
How Does It Work?
In a post on their blog, the company disclosed that “using historic flight status data, our machine learning algorithms can predict some delays even when this information isn’t available from airlines yet…”
The algorithm would inform users when their flight could be delayed only if it predicts that there was an 80% chance that it would. The information will appear in search results when you look up your flight number, route, or airline.
Artificial Intelligence continues to blossom
The feature once again captures the importance of machine learning development. The algorithm would filter through rapidly changing data and find patterns to use as signals. From there, it could make predictions and use its past predictions to make improved predictions.
Even though flight companies could send some data, the algorithm would still rely heavily on examining other data, such as weather and location, to make predictions.
Google Flights not a perfect system and not available everywhere
Now there is one thing you should note though. It is not a perfect prediction. And Google still advises that passengers arrive early at the airport.
Additionally, the service is not yet globally available. It is only available to less than 50 countries presently. It is not supported in Nigeria and other African countries yet.
I sent an email to Google asking when Nigerians and Africans can begin to enjoy the service. No feedback has been received at the time this post was published.
Machine learning In Nigeria?
Nonetheless, the prediction made by Google Flights is another win for machine learning and artificial intelligence. Both tech trends are becoming more and more important in our daily lives. Nigerian companies are now developing such technologies too.
Bounce.ng, a news aggregator app, uses machine learning algorithm to study your news reading habits. After using the app for a couple of times, it begins to make article recommendations for you.
Paylater.ng is another app that uses some AI to check your credit worthiness before it grants you loans. Using machine learning techniques, Paylater.ng can give out loans up to N1,000,000 to people with less stress than banks.
So we should be expecting more AI powered system from both Nigerian and foreign companies. An interesting trend to cover no doubt.
Get the best of Africa’s daily tech to your inbox – first thing every morning.
Join the community now!