Assessing the predictive value of traffic count data in the imputation of on-street parking occupancy in Amsterdam

Pablo Martín Calvo*, Bas Schotten, Elenna R. Dugundji

*Corresponding author for this work

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

On-street parking policies have a huge impact on the social welfare of citizens. Accurate parking occupancy data across time and space is required to properly set such policies. Different imputation and forecasting models are required to obtain this data in cities that use probe vehicle measurements, such as Amsterdam. In this paper, the usage of traffic data as an explanatory variable is assessed as a potential improvement to existing parking occupancy prediction models. Traffic counts were obtained from 164 traffic cameras throughout the city. Existing models for predicting parking occupancy were reproduced in experiments with and without traffic data, and their performance was compared. Results indicated that (i) traffic data are indeed a useful predictor and improves performance of existing models; (ii) performance does not improve linearly with an increase in the number of counting points; and (iii) placement of the cameras does not have a significant impact on performance.

Original languageEnglish
Pages (from-to)330-341
Number of pages12
JournalTransportation Research Record
Volume2675
Issue number12
Early online date30 Aug 2021
DOIs
Publication statusPublished - 1 Dec 2021

Bibliographical note

Publisher Copyright:
© National Academy of Sciences: Transportation Research Board 2021.

Fingerprint

Dive into the research topics of 'Assessing the predictive value of traffic count data in the imputation of on-street parking occupancy in Amsterdam'. Together they form a unique fingerprint.

Cite this