Creating and sharing knowledge for telecommunications

On Predicting the Taxi-Passenger Demand: A Real-Time Approach

Matias, L. ; Gama, J.G. ; Ferreira, M. ; João Mendes-Moreira, JMM ; Damas, L.D.

On Predicting the Taxi-Passenger Demand: A Real-Time Approach, Proc Portuguese Conf. on Artificial Intelligence - EPIA, Angra do Heroísmo, Portugal, Vol. XX, pp. XX - XX, September, 2013.

Digital Object Identifier: 0

Download Full text PDF ( 1 MB)

Abstract
Informed driving is becoming a key feature to increase the sustainability of taxi companies. Some recent works are exploring the data broadcasted by each vehicle to provide live information for decision making. In this paper, we propose a method to employ a learning model based on historical GPS data in a real-time environment. Our goal is to predict the spatiotemporal distribution of the Taxi-Passenger demand in a short time horizon. We did so by using learning concepts originally proposed to a well-known online algorithm: the perceptron. The results were promising: we accomplished a satisfactory performance to output the next prediction using a short amount of resources.