Farecast made some waves in the online travel business a few years ago when founder and University of Washington computer scientist Oren Etzioni came up with an algorithm to predict whether airfares on selected flights would go up or down.

That technology -- following Microsoft's acquisition of Farecast last year for $115 million -- now serves as the core of the new Bing Travel. But here's a unique twist on the Farecast concept. What if you could accurately predict which flights will be delayed? That's the idea behind a San Francisco startup called FlightCaster, which this week announced $1.3 million in funding from Sherpalo Ventures and others.

And there's still a chance that Amazon.com might get involved too, since FlightCaster is one of the seven finalists for the Amazon Web Services startup challenge. The winner of that event will be announced Dec. 9.

Here's what FlightCaster has to say about its technology:

"We are not regurgitating information from the airline or FAA. You can get that from many many other sources. Instead, we’re creating the next generation of flight information by using applied mathematics to provide real predictive power. While we cannot predict every scenario, such as a freak mechanical failure, our algorithms can find 95%+ of delays. Delay prediction is a bit of an art form and while we think we’re masters of that art, please allow room for error."

Of course, leaving room for error can be problematic when you are trying to make a connection or decide what time to show at the airport. That's something that TechCrunch points out in its post on the startup.