Mining ticketing logs for usage characterization with nonnegative matrix factorization

Abstract : Understanding urban mobility is a fundamental question for institutional organizations (transport authorities, city halls) and it involves many different fields like social sciences, urbanism or geography. With the increasing number of probes tracking human locations, like magnetic pass for urban transportation, road sensors, CCTV systems or cell phones, mobility data are exponentially growing. Mining the activity logs in order to model and characterize efficiently our mobility patterns is a challenging task involving large scale noisy datasets. In this article, we present a robust approach to characterize activity patterns from the activity logs of a urban transportation network. Our study focuses on the Paris subway network. Our dataset includes more than 80 millions travels by 600k users. The proposed approach is based on a multi-scale representation of the user activities, coupled to a nonnegative matrix factorization algorithm. The latter is used to learn dictionaries of usages that can be exploited in order to characterize user mobility and station visits patterns. The relevance of the extracted dictionaries is then assessed by using them to cluster users and stations. This analysis shows that public transportation usage patterns are tightly linked to sociological patterns.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01070359
Contributor : Mickaël Poussevin <>
Submitted on : Wednesday, October 1, 2014 - 10:37:37 AM
Last modification on : Thursday, March 21, 2019 - 2:30:50 PM
Document(s) archivé(s) le : Friday, January 2, 2015 - 10:41:40 AM

File

sensemlpoussevin.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01070359, version 1

Citation

Mickaël Poussevin, Nicolas Baskiotis, Vincent Guigue, Patrick Gallinari. Mining ticketing logs for usage characterization with nonnegative matrix factorization. SenseML 2014 -- ECML Workshop, Sep 2014, Nancy, France. ⟨hal-01070359⟩

Share

Metrics

Record views

209

Files downloads

202