Slashdot Mirror
Google Flights Will Now Predict Airline Delays -- Before the Airlines Do (techcrunch.com)
Google is rolling out a few new features to its Google Flights search engine to help travelers tackle some of the more frustrating aspects of air travel -- delays and the complexities of the cheaper, Basic Economy fares. From a report: With the regard to delays, Google Flights won't just be pulling in information from the airlines directly, however -- it will take advantage of its understanding of historical data and its machine learning algorithms to predict delays that haven't yet been flagged by airlines themselves. Explains Google, the combination of data and A.I. technologies means it can predict some delays in advance of any sort of official confirmation. Google says that it won't actually flag these in the app until it's at least 80 percent confident in the prediction, though.
I predict your flight will be delayed, odds are I'm right.
"Have you ever thought about just turning off the TV, sitting down with your kids, and hitting them?"
Some of the airline reservation services display an "ontime" percentage next to the flight - EG This flight is ontime 75% of the time.
You don't need machine learning for something that simple statistical analysis will do.
Unless Google's adding in a few factors into the model like weather and time of year.
Which leads to an interesting side-business. Gambling on "airline times."
Ahh the airfield is kinda muddy today and Frontier airlines always does better on a muddy track...
I fly on United regularly and one of my frustrations is that the airline is slow to update the status of flights that they should know are going to be late. Using their own smartphone app (or website) you can see the status of a given flight and can also easily navigate to the previous flight leg for where your plane is coming from. I have observed that it is very common for my flight to be listed as "on time" when the the app shows that the plane I am scheduled to be on is going to be late in arriving to the airport (making it physically impossible for my flight to be on time.) I get that the schedules have quite a bit of padding and that a short delay in an inbound flight doesn't necessarily mean that the outbound flight will end up be late in its ultimate destination, but when the airline knows that the inbound flight is going to be an hour late, it's shouldn't take half an hour for it to update the status of all the cascading delays. Perhaps Google can be more aggressive at prediction or maybe at least create some prediction competition so that United gets more timely with its updates.
Planes are pretty full these days and knowing 15 minutes earlier that you are going to miss a connection can easily make the difference as to if you can make other arrangements or not.
Yeah, no shit.
They know the plane you're flying hasn't left yet, and they know they don't have another plane for you.
So when that 4 hour incoming flight hasn't left yet, and yours is supposed to leave in 20 minutes, the airline bloody well knows this. But they will delay and stall admitting this for hours and pretend like it's a surprise to them.
The airline knows, they're just not going to tell you that.
I am never going to purchase a flight I don't earn miles on... determining when the cheapest qualifying flights are.
This pretty much explains why modern economy flying is so awful.
Some of the airline reservation services display an "ontime" percentage next to the flight - EG This flight is ontime 75% of the time. You don't need machine learning for something that simple statistical analysis will do.
You do if you want to provide better information than this. For example, I would be fine taking a flight which is 75% on time and the remaining 25% of the time is only 20 minutes late. I would be less happy if 25% of the time the flight was 2 hours late. Also this statistic ignores patterns in the delays. For example, suppose the flight is on time 90% of the time from Mon-Thu but delayed by 2 hours 85% of the time on Friday? This would be completely consistent with the data provided if you average over the week but clearly, you would never want to take this flight on Friday!
While you might be able to do a simple analysis on a weekly pattern airline schedules are more complex and if the delay is caused by a complex interaction of the crew, plane and airport schedules it will be a lot harder to pick up manually whereas a machine learning algorithm should easily be able to cope with this level of complexity and spot that on the third tuesday and second wednesday of every month your flight is delayed. In fact, if the airlines do not do this already, this might be a useful tool for them to spot and identify problems so they can fix them.
As in learning to come up with as many bullshit buzzwords they can fit into a sentence to describe what would otherwise be a pedestrian algorithm.
Largely true, but let's remember that the people giving you information about your late flight are as in the dark as you are.
I'm sure dispatch knows what's happening airline wide and how it's likely to affect the future schedule, but until it's been fully decided how to deal with the schedule impacts they don't start telling everybody because they are not totally sure.
Reasons not to communicate include the following: 1. Passengers may take other options. 2. They may be wrong about how long the delay will be, if they estimate too much delay, passengers get shuffled or are missing when they eventually try to board, if they estimate to little delay, passengers may be more angry than necessary with having to wait longer. 3. It's a lose/lose situation when you announce a delay.
"File to fit, pound to insert, paint to match" - Aircraft Maintenance 101
Just arrive at the airport 28 hours before your flight and you'll make it to the departure gate on time.
It'd also be nice to add a checked bag when you go into the comparison so you don't have to mentally track that.
if (strcmp(Carrier, "AA") == 0 || strcmp(Airport, "EWR") == 0) then DisplayDelay();
Sell advertising.
I'm a good cook. I'm a fantastic eater. - Steven Brust
Until a series of other delays has freed up a different plane that is already at the terminal and a simple gate change allows the original flight to leave on time.
Then your idiotic "80% correct" google algorithm has everyone off eating at a restaurant, booking hotel rooms, and/or generally unaware that there is not a 5 hour delay but instead you should be boarding right now.
The real power or killer app is Google Luggage Locator, followed closely by D00d where is my car? app.
International downloads cause a meltdown of the hosting servers =]
WARNING: Smartphones have side effects--most of them undocumented.
I think most aircraft already broadcast their location via ADS-B:
Flight info.
I don't know a lot about it but I believe people track these things for fun (& it sounds like fun too!). I would expect that they pour this info into a global database too. It would make sense for Google to tap this info and use a planes location & expected location as part of its prediction.
Actually, I think there's a scheme (possibly active) out to have LEO satellites tracking this info to mitigate the "lost aircraft" events that we had a cluster of not so long ago. It cost lots of $ trying to find planes full of people that disappear without a trace.
I wonder if SpaceX / RocketLab etc. have transponders? I would expect so but what about those military launches? Probably turned off for those...
Yes, it's called Kayak. Enter when and where you want to fly, select your airline alliance, and you're good to go.
Browsing at +1 - no ACs, I ignore their posts. So refreshing!
That's when they tell you there will be a 30 minute delay. I think its part of the stringing along / breaking it gently process.
Nullius in verba
I can't wait until Google predicts some jackwagon breaking a overhead bin while boarding because 'ITLL FIT IT ALWAYS FITS'.
...that's what she said...
ADSB antennas points to the ground and I'm not sure how well 1090Khz AM modulation would be heard in space..
Dang... there was supposed to be a question-mark at the end of my title... as in...
"Taps into ADS-B & open tracking of flight info?"
I don't know if Googles system actually does use ADS-B and was just pondering rather than stating (which it looks like without the "?")
One of the cause that you get the warning much later is because the app is getting directly message from the scheduling & operating system, while you get your warning from the RES (or sometimes CKI) systems. The airline backend are a series of interconnected systems and the time it takes to propagate or even the resource given are not the same. Most probably you were actually not buying your ticket directly from the airline but through an agency or a third party system. In which case your booking was in the GDS, and potentially you are not even getting in this case the "late" message from the airline, but through the GDS messaging from the stuff you have in your PNR : email or SMS.
If it was all one big system in the hand of the airline you would get your "late" warning probably more quickly. But this is not the case. Here google will probably tell you quicker, because the other side has to go through many legacy system, with many different protocols , some with no guaranted time but guaranted delivery among others it could be MATIP A, MATIP B, teletype, then to you it could be email and SMS. I am not even going into details here....
C. Sagan : A demon haunted world:
http://www.amazon.com/gp/product/0345409469/
visit randi.org
I do find that airlines seem to like to keep announcements about delays quiet until the last minute. Certainly in the UK they are rarely displayed before checkin (only after security, when you can't go back), which of course keeps you stuck in the airport where I suspect they hope you'll spend money in the shops during your delay. I find it can be useful to search for your flight on Flightradar or the like. They often have the registration of the aircraft booked to operate the flight (how they get this, I don't know), so it can be worth looking at the previous flight that aircraft is operating and see if that is late. If it is, it's likely you're flight will be too.