• DocumentCode
    2195022
  • Title

    Data Prediction Competitions -- Far More than Just a Bit of Fun

  • Author

    Goldbloom, Anthony

  • Author_Institution
    Kaggle, Melbourne, VIC, Australia
  • fYear
    2010
  • fDate
    13-13 Dec. 2010
  • Firstpage
    1385
  • Lastpage
    1386
  • Abstract
    Data prediction competitions facilitate a step change in the evolution of analytics outsourcing. They offer companies and researchers a cost effective way to harness the `cognitive surplus´ of data scientists who are hungry for real-world data and motivated to excel whatever the prize. Competitions are effective because there are any number of techniques that can be applied to any modeling problem but we can´t know in advance which will be most effective. By exposing the problem to a wide audience, competitions are an effective way to reach the frontier of what is possible from a given dataset.
  • Keywords
    data mining; analytics outsourcing; cognitive surplus; data prediction competition; bioinformatics; competitions; crowdsourcing; data mining; machine learning; statistics;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Data Mining Workshops (ICDMW), 2010 IEEE International Conference on
  • Conference_Location
    Sydney, NSW
  • Print_ISBN
    978-1-4244-9244-2
  • Electronic_ISBN
    978-0-7695-4257-7
  • Type

    conf

  • DOI
    10.1109/ICDMW.2010.56
  • Filename
    5693459