Survey and empirical evaluation of nonhomogeneous arrival process models with taxi data

Hamid R. Sayarshad, Joseph Ying Jun Chow

Research output: Contribution to journalArticle

Abstract

Arrival processes are important inputs to many transportation system functions, such as vehicle prepositioning, taxi dispatch, bus holding strategies, and dynamic pricing. We conduct a comprehensive survey of the literature which shows that many transport systems employ basic homogeneous arrival process models or static nonhomogeneous processes. We conduct an empirical experiment to compare five state of the art arrival process short term prediction models using a common transportation system data set: New York taxi passenger pickups in 2013. Pickup data is split between 672 observations for model estimation and 96 observations for validation. From our experiment, we obtain evidence to support a recent model called FM-IntGARCH, which is able to combine the benefits of both time series models and discrete count processes. Using a set of seven performance metrics from the literature, FM-IntGARCH is shown to outperform the offline models-seasonal factor method, piecewise linear model-as well as the online models-ARIMA, Gaussian Cox process. Implications for operating data-driven "smart" transit systems and urban informatics are discussed.

Original languageEnglish (US)
JournalJournal of Advanced Transportation
DOIs
StateAccepted/In press - 2016

Fingerprint

Pickups
Process model
Empirical evaluation
Time series
Experiments
Experiment
Costs
Dynamic pricing
Factors
Time series models
Bus
Performance metrics
Prediction model
Informatics
ARIMA models
Cox process

Keywords

  • Arrival process
  • Gaussian Cox process
  • New York taxi data
  • Non-homogeneous Poisson process
  • Time series

ASJC Scopus subject areas

  • Strategy and Management
  • Economics and Econometrics
  • Mechanical Engineering
  • Computer Science Applications
  • Automotive Engineering

Cite this

@article{e4f3268ad1c84481844a750826e48685,
title = "Survey and empirical evaluation of nonhomogeneous arrival process models with taxi data",
abstract = "Arrival processes are important inputs to many transportation system functions, such as vehicle prepositioning, taxi dispatch, bus holding strategies, and dynamic pricing. We conduct a comprehensive survey of the literature which shows that many transport systems employ basic homogeneous arrival process models or static nonhomogeneous processes. We conduct an empirical experiment to compare five state of the art arrival process short term prediction models using a common transportation system data set: New York taxi passenger pickups in 2013. Pickup data is split between 672 observations for model estimation and 96 observations for validation. From our experiment, we obtain evidence to support a recent model called FM-IntGARCH, which is able to combine the benefits of both time series models and discrete count processes. Using a set of seven performance metrics from the literature, FM-IntGARCH is shown to outperform the offline models-seasonal factor method, piecewise linear model-as well as the online models-ARIMA, Gaussian Cox process. Implications for operating data-driven {"}smart{"} transit systems and urban informatics are discussed.",
keywords = "Arrival process, Gaussian Cox process, New York taxi data, Non-homogeneous Poisson process, Time series",
author = "Sayarshad, {Hamid R.} and Chow, {Joseph Ying Jun}",
year = "2016",
doi = "10.1002/atr.1401",
language = "English (US)",
journal = "Journal of Advanced Transportation",
issn = "0197-6729",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Survey and empirical evaluation of nonhomogeneous arrival process models with taxi data

AU - Sayarshad, Hamid R.

AU - Chow, Joseph Ying Jun

PY - 2016

Y1 - 2016

N2 - Arrival processes are important inputs to many transportation system functions, such as vehicle prepositioning, taxi dispatch, bus holding strategies, and dynamic pricing. We conduct a comprehensive survey of the literature which shows that many transport systems employ basic homogeneous arrival process models or static nonhomogeneous processes. We conduct an empirical experiment to compare five state of the art arrival process short term prediction models using a common transportation system data set: New York taxi passenger pickups in 2013. Pickup data is split between 672 observations for model estimation and 96 observations for validation. From our experiment, we obtain evidence to support a recent model called FM-IntGARCH, which is able to combine the benefits of both time series models and discrete count processes. Using a set of seven performance metrics from the literature, FM-IntGARCH is shown to outperform the offline models-seasonal factor method, piecewise linear model-as well as the online models-ARIMA, Gaussian Cox process. Implications for operating data-driven "smart" transit systems and urban informatics are discussed.

AB - Arrival processes are important inputs to many transportation system functions, such as vehicle prepositioning, taxi dispatch, bus holding strategies, and dynamic pricing. We conduct a comprehensive survey of the literature which shows that many transport systems employ basic homogeneous arrival process models or static nonhomogeneous processes. We conduct an empirical experiment to compare five state of the art arrival process short term prediction models using a common transportation system data set: New York taxi passenger pickups in 2013. Pickup data is split between 672 observations for model estimation and 96 observations for validation. From our experiment, we obtain evidence to support a recent model called FM-IntGARCH, which is able to combine the benefits of both time series models and discrete count processes. Using a set of seven performance metrics from the literature, FM-IntGARCH is shown to outperform the offline models-seasonal factor method, piecewise linear model-as well as the online models-ARIMA, Gaussian Cox process. Implications for operating data-driven "smart" transit systems and urban informatics are discussed.

KW - Arrival process

KW - Gaussian Cox process

KW - New York taxi data

KW - Non-homogeneous Poisson process

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=84980018991&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84980018991&partnerID=8YFLogxK

U2 - 10.1002/atr.1401

DO - 10.1002/atr.1401

M3 - Article

JO - Journal of Advanced Transportation

JF - Journal of Advanced Transportation

SN - 0197-6729

ER -