IEEE ICDM 2010 Contest TomTom Traffic Prediction for Intelligent GPS Navigation Marcin Wojnarski * , Pawel Gora † , Marcin Szczuka † , Hung Son Nguyen † , Joanna Swietlicka * and Demetris Zeinalipour ‡ * TunedIT Solutions, Zwirki i Wigury 93/3049, 02-089 Warsaw, Poland Email: {marcin.wojnarski,j.swietlicka}@tunedit.org † Faculty of Mathematics, Informatics and Mechanics, The University of Warsaw, Banacha 2, 02-097 Warsaw, Poland Email: {pawelg,szczuka,son}@mimuw.edu.pl ‡ Department of Computer Science, University of Cyprus, 1678 Nicosia, Cyprus Email: dzeina@cs.ucy.ac.cy Abstract—In this foreword, we summarize the IEEE ICDM 2010 Contest: “TomTom Traffic Prediction for Intelligent GPS Navigation”. The challenge was held between Jun 22, 2010 and Sep 7, 2010 as an interactive on-line competition, using the TunedIT platform (http://tunedit.org). We present the scope of the ICDM contest series in general, the scope of this year’s contest, description of its tasks, statistics about participation, details about the TunedIT platform and the Traffic Simulation Framework. A detailed description of winning solutions is part of this proceeding series. Keywords-Contest, TomTom, TunedIT, traffic, simulation, prediction, data mining, Warsaw I. THE ICDM DATA MINING (DM) CONTEST The ICDM Data Mining Contest offers a unique opportu- nity to scientists and enterprises, to involve teams of domain experts that will compete against each other in order to develop and test data mining techniques that can improve real or realistic applications. The general philosophy of the contest is to provide to participants a set of custom datasets, evaluation metrics (or software tools) as well as expected answers to a set of predetermined tasks. The participants are then asked to identify the best possible solutions to the given tasks maximizing the given evaluation metrics. Competing team work off-line to implement the tasks outlined by the contest organizers. The results of each team are then submitted to the organizers prior the conference date. The contest organizers select the submissions that will be included in the proceedings of the conference. The awarding process is carried out during the conference. The previous ICDM DM contests were organized as follows: In 2007, the Hong Kong University of Science and Technology (Hong Kong) organized a competition in Om- aha, NE (USA) with title: “Estimating Location Using Wi- Fi” (http://www.cse.ust.hk/˜qyang/ICDMDMC07/). In 2008, the University of Ottawa (Canada), the Universiteit Utrecht (Netherlands) and Health Canada (Canada) organized a competition in Pisa, Italy with title: “Radioxenon moni- toring for verification of the Comprehensive nuclear-Test- Ban Treaty” (http://www.cs.uu.nl/groups/ADA/icdm08cup/). In 2009, the Walt Schneider Research Lab at the Uni- versity of Pittsburgh (USA) organized a competition in Miami, FL USA with title: “The Pittsburgh Brain Competi- tion” (http://pbc.lrdc.pitt.edu/). This year, TunedIT Solutions (Poland), the University of Warsaw (Poland) and TOMTOM International BV (The Netherlands), organize a competition in Sydney Australia with title: “Traffic Prediction for Intel- ligent GPS Navigation” (http://tunedit.org/challenge/IEEE- ICDM-2010) II. THE 2010 CONTEST DESCRIPTION Over the last century the number of cars engaged in vehicular traffic in cities has increased rapidly, causing many difficulties for all citizens: traffic jams, large and unpre- dictable communication delays, pollution etc. Excessive traf- fic became a civilization problem that affects everyone who lives in a city of 50,000 or larger, anywhere in the world. Complexity of processes that stand behind traffic flow is so large, that only data mining algorithms may bring efficient solutions. With the IEEE ICDM 2010 Contest, the organizers asked researchers to devise the best possible algorithms that tackle problems of traffic flow prediction, for the purpose of intelligent driver navigation and improved city planning. The challenge was organized in the form of an in- teractive on-line competition, at TunedIT platform, be- tween June 22, 2010 and September 7, 2010. The winners were awarded prizes worth $5000, sponsored by TomTom (http://www.tomtom.com/). Organizing Committee of the challenge consisted of four members: Marcin Wojnarski, Pawel Gora, Hung Son Nguyen and Marcin Szczuka. The contest was sub-divided into three independent tasks: 1) Task 1 – Traffic congestion prediction, in an ele- mentary setup of time series forecasting: a series of measurements from 10 selected road segments is given