Open Collaboration Innovations Could Transform Air Travel
GE and partners have revealed the winners of the first “Industrial Internet Quests,” an open innovation challenge to create new algorithms to reduce air travel delays and design applications to improve the healthcare experience. Launched in November 2012 in collaboration with Kaggle, a leading platform in solving data science challenges, and with Alaska Airlines and Ochsner Health System, the Quests invited data scientists and designers to use analytics and design to find ways to increase efficiency for airlines, travelers, hospitals and patients. The Quests are part of a broader effort to create an open platform, cultivate a community, and develop Industrial Internet solutions.
Developers and data scientists representing 58 countries submitted more than 3,000 combined ideas. A total prize pool of $600,000 in cash awards will be distributed among the winners of both Quests. Kaggle’s live leaderboard scored the Flight Quest algorithms, determining the most accurate predictive models compared to the industry benchmark.
Gary Beck, Alaska Airlines’ vice president of flight operations said, “Predicting arrival times more accurately offers several benefits. Improved accuracy can help us avoid gate congestion, minimizing delays for passengers and crews. It means less wait time and better efficiency for ground crews. And, ultimately, it means more efficient use of our aircraft, which saves fuel and helps us offer low fares. GE is continually pushing innovation and we look forward to continuing our partnership with GE in Flight Quest II to help pilots make smarter in-flight decisions.”
Using national airspace data, made available for the first time for an open data analytics challenge, the winning Flight Quest algorithms show a 40% improvement over the industry benchmark of seven minutes average error in predicted arrival time. This has the potential to save travelers more than five minutes at the gate and could translate to significant savings for airlines. A one-minute reduction per departure could save an average-sized airline 1,700 hours per year, the equivalent of reducing crew costs by $1.2 million and fuel costs by $5 million.
Flight Quest participants received a two-month data set of flight information of the National Airspace System including flight number, origin, destination, take-off time, arrival time, latitude and longitude at frequent interim waypoints along the journey, and weather and wind data. They used this to develop algorithms to better predict time of arrivals at run-ways and gates to improve the efficiency in how airlines fly their planes, better balancing cost and customer satisfaction.
The winners include:
- 1st Prize - Gxav &*: Xavier Conort, Cao Hong, Clifton Phua, Ghim-Eng Yap and Kenny Chua (Singapore)
- 2nd Prize - As High as Honor: Jonti Peters (Preston, UK) and Pawel Jankiewicz (Warsaw, Poland)
- 3rd Prize - Taki: Gabor Takacs (Gyor, Hungary)
- 4th Prize - Sun: Sergey Kozub (Russia)
- 5th Prize - Jacques Kvam: Jacques Kvam (USA)
“The latest advancements in real-time big data analytics are already changing the course of flight, and the results of the Flight Quest prove that," said Pawel Jankiewicz, a winner of the Flight Quest. "It’s a thrill to know that something my team developed will have a profound effect on the aviation industry and save millions of dollars. Ultimately, we’re excited to see our, and the other contestants’, work implemented and for future collaboration with GE.”
Bolen Gives Congress a Rare Thumbs-Up
See All