Probabilistic Traffic Forecasting with Dynamic Regression

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zheng, Vincent Zhihao, Choi, Seongjin, Sun, Lijun
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916677055152128
author Zheng, Vincent Zhihao
Choi, Seongjin
Sun, Lijun
author_facet Zheng, Vincent Zhihao
Choi, Seongjin
Sun, Lijun
contents This paper proposes a dynamic regression (DR) framework that enhances existing deep spatiotemporal models by incorporating structured learning for the error process in traffic forecasting. The framework relaxes the assumption of time independence by modeling the error series of the base model (i.e., a well-established traffic forecasting model) using a matrix-variate autoregressive (AR) model. The AR model is integrated into training by redesigning the loss function. The newly designed loss function is based on the likelihood of a non-isotropic error term, enabling the model to generate probabilistic forecasts while preserving the original outputs of the base model. Importantly, the additional parameters introduced by the DR framework can be jointly optimized alongside the base model. Evaluation on state-of-the-art (SOTA) traffic forecasting models using speed and flow datasets demonstrates improved performance, with interpretable AR coefficients and spatiotemporal covariance matrices enhancing the understanding of the model.
format Preprint
id arxiv_https___arxiv_org_abs_2301_06650
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Probabilistic Traffic Forecasting with Dynamic Regression
Zheng, Vincent Zhihao
Choi, Seongjin
Sun, Lijun
Machine Learning
This paper proposes a dynamic regression (DR) framework that enhances existing deep spatiotemporal models by incorporating structured learning for the error process in traffic forecasting. The framework relaxes the assumption of time independence by modeling the error series of the base model (i.e., a well-established traffic forecasting model) using a matrix-variate autoregressive (AR) model. The AR model is integrated into training by redesigning the loss function. The newly designed loss function is based on the likelihood of a non-isotropic error term, enabling the model to generate probabilistic forecasts while preserving the original outputs of the base model. Importantly, the additional parameters introduced by the DR framework can be jointly optimized alongside the base model. Evaluation on state-of-the-art (SOTA) traffic forecasting models using speed and flow datasets demonstrates improved performance, with interpretable AR coefficients and spatiotemporal covariance matrices enhancing the understanding of the model.
title Probabilistic Traffic Forecasting with Dynamic Regression
topic Machine Learning
url https://arxiv.org/abs/2301.06650