Real-Time Traffic Prediction Using GPS Data with Low Samping Rates: A Hybrid Approach

This paper presents an approach for real-time traffic speed prediction via GPS speed readings. The approach combines techniques from data mining with traffic speed estimates available from other sources. In particular, we consider GPS data that is provided in the form of point speeds, rather than trajectories. This is the case when GPS data from consumers is sampled at discrete points by a service provider, e.g. to protect privacy of the consumers by not permitting a reconstruction of their trajectories. In the context studied in this paper as well as others observed in practice, such GPS sampling rates are quite low and hence the GPS-based speed readings can be quite unreliable. Our method recognizes this fact and uses the GPS speed readings in a novel way in conjunction with another source of speed data for the network. The example studied is drawn from the 2010 IEEE International Competition on Data Mining (ICDM) traffic prediction competition, in which the authors were part of a team that finished second worldwide.

By: Wei Shen; Laura Wynter

Published in: RC25230 in 2011


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to .