日時：3月20日（水）　15：00-16:30

場所：京都大学桂キャンパスCクラスター C1-117（C棟会議室1）

http://www.kyoto-u.ac.jp/ja/access/campus/map6r_k.htm

講師：Prof. Stephane Hess, University of Leeds, UK

題目：Using big data for modelling human decision making

Abstract: Traditional data sources like household surveys are expensive to collect and sueveys are thus not conducted at regular enough intervals nor do they collect samples large enough to be representative or reliable for complex model estimation. On the other hand, very large streams of data are collected automatically from people every day, most notably in the form of mobile phone records and smart card data. While such data sourves have been used extensively for visualisarion or even in machine learning, their use in traditional transport modelling is still in its infancy. This presentation presents some ground-breaking work in this area, showing how smartcard, GPS and mobile phone data can be exploited for modelling a veriety of transport decisions and producing meaningful results. The presentation also looks at some of the steps required to make the data usable for analysis. The talk will provide a methodological overview meant to stimulate discussion. Part of the talk will also be a range of application studies, among others on tourism and evacuation modelling.

About the speaker: Stephane Hess is Professor of Choice Modelling in the Institute for Transport Studies and Director of the Choice Modelling Cntre at the University of Leeds. He is also Honorary Professor in Choice Modelling in the Institute for Transport and Logistices Studies at the University of Sydney, Honorary Professor of Modelling Behaviour in Africa at the University of Cape Town. His area of work is the analysis of human decision making using advanced mathematical models. He has made contoributions to the state of  the art in the specification, estimation and interpretation of such models, as well as in facilitating the transition of ideas and approaches across disciplines. Together with his research team at the Choice Modelling Centre, he is setting the research agenda in applying choice modelling in new fields, including education, lifestyle choices, social (network) interactions and joint decision making. Advanced choice models require high quality data, and Hess and his team are leading the field in exploring and exploring novel data sources, with numerous applications using  “big data”.  Hess has published over 100 peer reviewed journal papers, and his work is highly cited, with a Scopus H-index of 28 (google scholar H-index of 45). HIs cotributions have been recognised for example by the 2017 ICMC award for the most innvative application of chice modelling, the 2014 Outstanding Young Member of the Transporation Research Board (TRB) award for exceptional achievements in transportation research, policy, or practice, the 2010 Fred Burggraf award handed out by the Transportation Research Board and the 2005 Eric Pas award for the best PhD thesis in the area of travel behaviour modelling. He is also the founding editor in chief of the Journal of Choice Modelling and the founder and steering committee chair of the International Choice Modelling Conference.

参加申し込み先:  Jan-Dirk Schmöcker (PhD), Associate Professor
Department of Urban Management, Kyoto University
C1-2-436, Katsura Nishikyo-ku, Kyoto 615-8540, Japan
Tel : +81-75-383-3234, Fax: +81-75-383-3236
schmoecker@trans.kuciv.kyoto-u.ac.jp
http://trans.kuciv.kyoto-u.ac.jp/its/Schmoecker.html