Data-driven Prediction Games

Abstract

More datasets are becoming available on the web. This provides new opportunities for data-driven systems that can entertain and inform. We introduce prediction games, data-driven games modeled after fantasy sports. We hypothesize that prediction games can motivate people to explore and analyze online datasets in order to develop their own understanding of the data's domain and to improve their data analysis skills. The mechanics of prediction games revolve around activities where players analyze historical data and information resources to make predictions about future events. This paper describes the iterative design of a prediction game engine and one of its implementations: Fantasy Climate.