Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction

Xinke Jiang, Dingyi Zhuang, Xianghui Zhang, Hao Chen, Jiayuan Luo +1 more
6/16/2023
cs.LGstat.MLstat.OT

No official code found. Best implementation: STTDAnonymous/STTD (19 stars, MIT, last commit 2023-09-17).

Abstract

Understanding Origin-Destination (O-D) travel demand is crucial for transportation management. However, traditional spatial-temporal deep learning models grapple with addressing the sparse and long-tail characteristics in high-resolution O-D matrices and quantifying prediction uncertainty. This dilemma arises from the numerous zeros and over-dispersed demand patterns within these matrices, which challenge the Gaussian assumption inherent to deterministic deep learning models. To address these challenges, we propose a novel approach: the Spatial-Temporal Tweedie Graph Neural Network (STTD). The STTD introduces the Tweedie distribution as a compelling alternative to the traditional 'zero-inflated' model and leverages spatial and temporal embeddings to parameterize travel demand distributions. Our evaluations using real-world datasets highlight STTD's superiority in providing accurate predictions and precise confidence intervals, particularly in high-resolution scenarios.

View on arXivView PDF

Code Implementations(1)

STTDAnonymous/STTDCommunity100%
MIT

Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction

192PythonJun 15, 20233 years agoMIT

Similar Papers

Uncertainty Quantification of Spatiotemporal Travel Demand with Probabilistic Graph Neural Networks

88% match2023

STEF-DHNet: Spatiotemporal External Factors Based Deep Hybrid Network for Enhanced Long-Term Taxi Demand Prediction

83% match2023

Spatio-temporal Prediction of Fine-Grained Origin-Destination Matrices with Applications in Ridesharing

83% match2025

Adaptive Modeling of Uncertainties for Traffic Forecasting

83% match1 repo62023

Improving Demand Forecasting in Open Systems with Cartogram-Enhanced Deep Learning

82% match2024

Multi-Graph Inductive Representation Learning for Large-Scale Urban Rail Demand Prediction under Disruptions

82% match2024

Cite this paper

@article{jiang2023uncertainty,
  title  = {Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction},
  author = {Xinke Jiang and Dingyi Zhuang and Xianghui Zhang and Hao Chen and Jiayuan Luo and Xiaowei Gao},
  year   = {2023},
  eprint = {2306.09882},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.09882v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.09882.svg)](https://codeofpaper.com/paper/2306.09882)

Discussion