A Neighborhood-Augmented LSTM Model for Taxi-Passenger Demand Prediction

authored by

Tai Le Quy, Wolfgang Nejdl, Myra Spiliopoulou, Eirini Ntoutsi

Abstract

Taxi is a convenient means of transportation worldwide. Accurately predicting the taxi-demand is crucial for taxi-companies to effectively allocate their fleet to taxi-stands and reduce the waiting time for passengers thus increasing their overall satisfaction and customer retention. Nowadays precise information about taxi-rides is available and can be used to infer the taxi-passenger demand across different locations and time-points. In this paper, we propose an approach for predicting the pick-demand of a given taxi-stand, that takes into account not only the demand-history of the particular stand but it also considers information from neighboring stands. Our model is an LSTM neural network augmented with information from the spatial neighborhood of the stands. Experiments with two versions of the taxi demand dataset from the city of Porto, Portugal show that our approach can provide better predictions comparing to approaches that do not exploit the neighborhood.

Organisation(s)

L3S Research Centre

External Organisation(s)

Otto-von-Guericke University Magdeburg

Type

Conference contribution

Pages

100-116

No. of pages

17

Publication date

04.01.2020

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

Theoretical Computer Science, Computer Science(all)

Sustainable Development Goals

SDG 11 - Sustainable Cities and Communities

Electronic version(s)

https://doi.org/10.1007/978-3-030-38081-6_8 (Access: Open)