To provide better services to their customers and to optimise their resources, airports and airline companies need to forecast the number of air passengers, their destination, or their intended travel time. However, the factors motivating European citizens to travel can not easily be identified through human expertise alone as the number of potential influencing parameters is too large
. AIRFORCE evaluates the contribution of advanced statistical methods, combining intelligent agents and data mining algorithms to forecast the number of air passengers for various destinations in Europe; it develops methods which enable limited sets of influencing parameters from huge amounts of data to be automatically extracted; it identifies generic rules which enable results to be extrapolated for departure destination pairs for which few data are available; it develops methods for obtaining the relevant data from existing data bases or the Internet in an intelligent way to be fed to a forecast server.
The main contribution of DFKI consists of multi-lingual information extraction from relevant WWW documents. Besides english, documents in german, french and italian will also be processed. The extracted information is augmented and adapted for use by the forecast server.
A result of the project will be a database of European events and trends, helping to identify what's going on where, how many people travel when, which region is growing, etc.
Sofresud, Frankreich (Koordinator); DFKI GmbH, Deutschland; Air France, Frankreich; Air Support, Italien; GESAC Flughafen Neapel, Italien