Modeling Censored Mobility Demand Through Censored Quantile Regression Neural Networks

Research output: Contribution to journalJournal articleResearchpeer-review

22 Downloads (Pure)


Shared mobility services require accurate demand models for effective service planning. On the one hand, modeling the full probability distribution of demand is advantageous because the entire uncertainty structure preserves valuable information for decision-making. On the other hand, demand is often observed through the usage of the service itself, so that the observations are censored, as they are inherently limited by available supply. Since the 1980s, various works on Censored Quantile Regression models have performed well under such conditions. Further, in the last two decades, several papers have proposed to implement these models flexibly through Neural Networks. However, the models in current works estimate the quantiles individually, thus incurring a computational overhead and ignoring valuable relationships between the quantiles. We address this gap by extending current Censored Quantile Regression models to learn multiple quantiles at once and apply these to synthetic baseline datasets and datasets from two shared mobility providers in the Copenhagen metropolitan area in Denmark. The results show that our extended models yield fewer quantile crossings and less computational overhead without compromising model performance.

Original languageEnglish
Article number21754
JournalIEEE Transactions on Intelligent Transportation Systems
Issue number11
Number of pages13
Publication statusPublished - 2022

Bibliographical note

Publisher Copyright:


  • Bayes methods
  • Bayesian modeling
  • Biological neural networks
  • Censored quantile regression
  • Censorship
  • Computational modeling
  • Computer architecture
  • Data models
  • deep learning
  • demand modeling
  • latent mobility demand
  • multi-task learning
  • Uncertainty


Dive into the research topics of 'Modeling Censored Mobility Demand Through Censored Quantile Regression Neural Networks'. Together they form a unique fingerprint.

Cite this