Flightcaster is all about the probability of being delayed though. The big customer is business users who will rebook on a flight that has less of a chance of delay. Airlines don't want that.
False positives are a killer to the airlines - they don't want to risk losing customers to another flight/airline when there will actually be no delay.
To customers, false positives are likely to be a minor issue though, probably the number of true positives will outweigh occasional false positives.
But without a false positive rate near 0, I can't imagine the airlines themselves being too interested in flightcaster's predictions.
FlightCaster lies in the predictive equivalent of the 'uncanny valley'. The problem with this kind of service is that while even 90% accuracy would be a great technical achievement, even 99% accuracy is probably insufficient for practical use. How many people actually change their arrangements because FlightCaster 'thinks' the flight is delayed vs those who simply wait to hear the official word? My guess is, not enough to build a business on.
There's a few metrics the airlines care about, the most important is leaving the gate on time. But once you're on the plane they can make you sit there for however long it is to sit on the tarmac.
When I was flying constantly for a month, almost all my flights were on time. FlightCaster did predict 2 flights that were to be delayed despite the planes pushing off on time. We just sat on the tarmac, upwards of an hour, before finally taking off.
By the same token, FlightCaster didn't predict the three other flights I was on that was delayed.
Either way, the use case is kind of limited. Even if the prediction is true and given enough warning ahead of time I have no means, and in most cases no need, to switch flights. For business travelers that have the expense accounts to make this work, this is a great tool.
This is an intriguing idea, but the problem I see is that airlines will not rebook you (fee-free, at least) until their own internal procedures have declared a delay or cancellation of a flight. By that point having the intel becomes useless.
It depends on who "you" are in this example. If you're someone who is flying for personal reasons or non-mission critical business reasons, then you're 100% right - knowing ahead you'll probably be late is interesting, but not enough to do anything about since you don't want to pay change/cancellation fees. I'm this guy when I travel for personal reasons.
But I also travel a lot for business, and when I do, travel is 100% critical. If I don't show up when I am scheduled to, there will often be several thousand people - not to mention three national news networks - waiting for me and my traveling party. Those people won't wait around, and will embarrass me and my people on a national stage.
Hence, for business travel, I use a travel management company for all my movements. I fly full-fare economy (so there are effectively no penalties to change my flights), and have a someone who gets paid a significant commission to monitor the status of my travel plans and adjust them on the fly based on weather and traffic conditions. Maybe 1.5 times per month I'll get a call/email from my travel guy some time between a day and a few hours before my departure telling me something has changed - either my routing or my departure time (incidentally, my travel guy is the only person outside my team who has access to our detailed daily calendar, so he can adjust for this).
I have no doubt that my travel manager would pay good money for this information, if it was statistically reliable. For people who travel for fun, I think you're right - a delay isn't a delay until the airline says it is. But for people who absolutely have to get where they're going - to the level that they'll charter a plane on an hours' notice if needed - this would be invaluable.
"I work in a moderately-progressive workplace, and if I ever need to seek the input of a supervisor on a big issue/something that may come back to haunt me, I'll talk to them about it, and then send them an email saying what we decided. This makes it clear what the decisions was (and more importantly, how I interpret it) and provides documentation to both sides that the issue was discussed and a conclusion reached."
"When I know I am wrapping up a coding session, I'll often leave a few trivial things unfinished - so that when I sit back down again for the next session, I'll have an easy place to jump right back in, and it will force me to (consciously or otherwise) get back to somewhere near the mental state I was in when I half-finished the thing."
Yes, I had the same idea after reading his comment above. I went back and read his last X comments.
He seems to be a Canada-based programmer.
EDIT: However:
"I mentioned that I've got no in-industry peer networking contacts, but I have a few very good ones in politics. Specifically, I've got a possible job offer through one to be one of the two or three advance guys for a very senior national politician. It would be a year of traveling around the country with them, likely including an election, and would be incredibly exciting."
Note: It is scary how much we reveal ourselves through our Internet postings
As for who/what I am, wallflower is correct in that I used to be a Canada-based programmer. While I'm still based here in Canada, I now do something 100% different (having nothing to do with software development) that necessitates this kind of travel.
Congratulations on getting to go behind-the-scenes in a way most of us only wonder what it could be like. A real "Ops" job.
I'm curious - how did you leverage your technical engineering ability to land the job, or was it more business/social acumen? I get a sense that you are very strategic from your advice about college to karate background. Especially, the novel idea about using Github to prove you wrote a paper (http://news.ycombinator.com/item?id=757295)
> If I don't show up when I am scheduled to, there will often be several thousand people - not to mention three national news networks - waiting for me and my traveling party. Those people won't wait around, and will embarrass me and my people on a national stage.
In partial defense of developer123 (partial because developer123 was created just yesterday to comment), I had to read back 156 days (and approximately that many comments) to find any substantiating evidence in JimmyL's historical comment stream that confirmed his seemingly ostentatious claims.
Up until that solitary (1/150+) comment, I thought I was right that the claims were suspicious.
All his historical comments pointed to a smart, opinionated, passionate, ambitious engineer (who did not seem to have the jet-setting job he talked about).
For example (130 days ago): "As a developer, I consider myself a "professional", and my life is fine with 6bit color. My roommate is a screenwriting "professional" and they're fine with 6bit color."
So I commented as such and resumed digging at T minus 130 only when I saw JimmyL's reply.
Can't really use searchyc.com for this (what keywords?).
Thanks Wallflower, yes I was hesitant about making that comment - I did research previous comments but not as far back as you did - I do think it's important to question authenticity of a comment esp. when it's a PRETAY big claim like above. If it's true - good luck to JimmeyL - if it's not he still seems to add a lot of value here with his comments.
I believe he has the position that he implied. However the tone of his message invited the find-fault investigation. It was a nice scavenger hunt. You were brave to confront his seemingly many-standard-deviations-removed-from-his-NewsYC-composite-comment-profile.
If someone says something to me, online or irl I tend to believe what it is that they say.
Maybe I should be more suspicious but I think that if you think it is 'brave' to start throwing suspicion in public as an anonymous newly signed up user to a forum that we probably have a different definition of 'brave'.
Fresh from my wedding, I waited in Dulles airport with my wife to take a trivial flight to JFK. From there, I would catch an international flight off to my honeymoon. Of course, things are never that easy.
It started with United claiming weather issues at JFK. Understandable, as getting delayed in to New York is a common occurrence. But we noticed things weren't adding up when the scheduled departure time would come and go while we were still on the ground. United delayed our flight -and no other- 30 minutes at a time for 6 hours straight.
I tried to find out what was going on. I checked FAA reports, I called multiple airline booths in both airports, no one could explain why -only- our flight was delayed and why it had been delayed for so long.
With FlightCaster, I get the ability to calculate opportunity cost. For my case, we missed our international connection, had to pay for a last-minute hotel in New York, and lost a day of our honeymoon. The direct cost to us, in both economical and emotional terms, was WAY higher than the cost of switching to a different flight.
Knowing the winning horse after the race is useless intel. But knowing which horse has a edge is powerful information before the fact.
This article explains it. 2 groups of people (1) they just want to know they might be late, telling their friends, etc (2) business travellers will pay to avoid the risk of a delayed flight
Flightcaster manages to predict ten times as many delays as the airlines do. And they manage to stay 90% accurate (which is on par with the airlines).
They're equally accurate, but predict ten times as many delays? Doesn't that imply that only a negligible percentage of flights are successfully predicted as delayed by either party?
Congrats, the b2b partnerships sounds like a solid business model. Plus it'd be easier to charge a frequently travelling exec for the service then the average consumer.
Hopefully the service can expand outside of the US. I see the limited/varied data of each country as the biggest technical hurdle they'll have to overcome.
Congrats, guys! I did quite a bit of traveling recently, and I found myself checking FlightCaster for a peace of mind. Great team, and a great product!
What does this mean? Do the airlines know about the potential delays but are unwilling to tell the public in most cases?
If Flightcaster really does have better tech than the airlines, then their major customers should be the airlines.