powered by kaggle

Completed • $220,000

Flight Quest 2: Flight Optimization, Final Phase

Sun 19 Jan 2014
– Sun 23 Feb 2014 (2 years ago)


view timeline »
  • August 6, 2013
    Competition Launch
  • September 25, 2013
    Milestone Entry Deadline
  • October 9, 2013
    Milestone winner announced
  • January 18, 2014
    Final model (agent) submissions deadline
  • February 13, 2014
    Final dataset released
  • February 23, 2014
    Final Submission Deadline

Prize Pool

view prizes »

1st $100,000
2nd $50,000
3rd $40,000
4th $30,000
Milestone $30,000 


Flight Quest Phase 2 Winners

Final Prizes

1st Prize: Jose Fonollosa

Jose A. R. Fonollosa has a M.S. and Ph.D. in electrical engineering from the Universitat Politëcnica de Catalunya (UPC, 1986 and 1989). He is a member of the Department of Signal Theory and Communications since 1986, currently as Full Professor, and visitor, from August 1991 to July 1992, of the Signal and Image Processing Institute, University of Southern California. Jose received the 1992 Marconi Young Scientist Award. He was co-founder (1999) of the company VERBIO S.L., specialised in spoken language technology. From 2006 to 2010, he was director of the Center for Language and Speech Technologies and Applications (TALP). He has published more than 150 scientific papers in statistical signal analysis, artificial intelligence, machine learning and optimization.

2nd Prize: Sergey Kozub

Sergey Kozub is an IT developer at Point Nine Financial Services, based in Cyprus. He received a Masters degree at Technical University of Moldova in 2003. He has competed in both GE Flight Quests, with remarkable results. His final model uses a mix of dynamic programming based on wind data and local search to optimize the evaluation estimate.

3rd Prize: Willem Mestrom

Willem Mestrom is a Business Intelligence specialist at Independer in The Netherlands. After earning his Master of Science at the University of Utrecht he worked for several years in IT. Later his interests shifted to research and analytics. He first learned about machine learning by competing in the Netflix Prize (member of team "The Ensemble") and later in several Kaggle competitions, most notably as a member of team POWERDOT in the Heritage Health Prize. He started on Flight Quest 2 for fun and because it would require a whole new set of skills -- as this was a very different kind of competition than anything he had worked on before.

4th Prize: Dmytro Lystopad

Dmytro Lystopad graduated from Kharkiv National University of Radio Electronics with a specialty in Intelligent Decision Support Systems. On his own time, Dmytro explores artificial intelligence and 3D graphics. His competition passion started with the Google AI Challenge 2011, which proposed to program ants' colony behaviour. From that derived his team name Murashka ("little ant" in translation) in other competitions. This also inspired Dmytro to use path search algorithms in GE Flight Quest 2 to find the optimal routes.

Milestone Prize: Team id

Roman A. Prokopenko (Moscow, Russian Federation)

Team id created an agent that optimized the cost function by selecting one of three actions for each time. Visit his forum post to learn more details.

Roman Prokopenko is a researcher at the Russian Academy of Sciences in the Institute of Higher Nervous Activity and Neurophysiology. He received his doctorate in physics and mathematics from Moscow Institute of Physics and Technology, State University in 2005. Having specialized in machine learning and control theory, Roman entered Flight Quest 2 for fun. Also, since Roman's brother is a professional pilot, he was enthusiastic to start an optimization problem in aviation.