eprintid: 3577
rev_number: 5
eprint_status: archive
userid: 69
dir: disk0/00/00/35/77
datestamp: 2016-10-06 15:10:59
lastmod: 2016-10-06 15:10:59
status_changed: 2016-10-06 15:10:59
type: conference_item
metadata_visibility: show
creators_name: Gast, Nicolas
creators_name: Massonnet, Guillaume
creators_name: Reijsbergen, Daniel
creators_name: Tribastone, Mirco
creators_id: 
creators_id: 
creators_id: 
creators_id: mirco.tribastone@imtlucca.it
title: Probabilistic Forecasts of Bike-Sharing Systems for Journey Planning
ispublished: pub
subjects: QA76
divisions: CSA
full_text_status: none
pres_type: paper
note: SCOPUS ID: 2-s2.0-84958242260
abstract: We study the problem of making forecasts about the future availability of bicycles in stations of a bike-sharing system (BSS). This is relevant in order to make recommendations guaranteeing that the probability that a user will be able to make a journey is sufficiently high. To do this we use probabilistic predictions obtained from a queuing theoretical time-inhomogeneous model of a BSS. The model is parametrized and successfully validated using historical data from the Vélib' BSS of the City of Paris.

We develop a critique of the standard root-mean-square-error (RMSE), commonly adopted in the bike-sharing research as an index of the prediction accuracy, because it does not account for the stochasticity inherent in the real system. Instead we introduce a new metric based on scoring rules. We evaluate the average score of our model against classical predictors used in the literature. We show that these are outperformed by our model for prediction horizons of up to a few hours. We also discuss that, in general, measuring the current number of available bikes is only relevant for prediction horizons of up to few hours.
date: 2015
date_type: published
publisher: ACM
pagerange: 703-712
event_title: 24th ACM International on Conference on Information and Knowledge Management
event_location: New York, USA
event_dates: 2015
event_type: conference
id_number: doi:10.1145/2806416.2806569
refereed: TRUE
isbn: 978-1-4503-3794-6
book_title: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15
official_url: http://doi.org/10.1145/2806416.2806569
citation:   Gast, Nicolas and Massonnet, Guillaume and Reijsbergen, Daniel and Tribastone, Mirco  Probabilistic Forecasts of Bike-Sharing Systems for Journey Planning.  In: 24th ACM International on Conference on Information and Knowledge Management, 2015, New York, USA pp. 703-712.  ISBN 978-1-4503-3794-6.      (2015)