Inverse optimization with endogenous arrival time constraints to calibrate the household activity pattern problem

Joseph Ying Jun Chow, Will W. Recker

Research output: Contribution to journalArticle

Abstract

A parameter estimation method is proposed for calibrating the household activity pattern problem so that it can be used as a disaggregate, activity-based analog of the traffic assignment problem for activity-based travel forecasting. Inverse optimization is proposed for estimating parameters of the household activity pattern problem such that the observed behavior is optimal, the patterns can be replicated, and the distribution of the parameters is consistent. In order to fit the model to both the sequencing of activities and the arrival times to those activities, an inverse problem is formulated as a mixed integer linear programming problem such that coefficients of the objectives are jointly estimated along with the goal arrival times to the activities. The formulation is designed to be structurally similar to the equivalent problems defined by Ahuja and Orlin and can be solved exactly with a cutting plane algorithm. The concept of a unique invariant common prior is used to regularize the estimation method, and proven to converge using the Method of Successive Averages. The inverse model is tested on sample households from the 2001 California Household Travel Survey and results indicate a significant improvement over the standard inverse problem in the literature as well as baseline prescriptive models that do not make use of sample data for calibration. Although, not unexpectedly, the estimated optimization model by itself is a relatively poor forecasting model, it may be used in determining responses of a population to spatio-temporal scenarios where revealed preference data is absent.

Original languageEnglish (US)
Pages (from-to)463-479
Number of pages17
JournalTransportation Research Part B
Volume46
Issue number3
DOIs
StatePublished - Mar 2012

Fingerprint

Inverse problems
travel
Parameter estimation
Linear programming
optimization model
time
Time constraints
Household
Calibration
programming
traffic
scenario
Inverse problem
literature
Revealed preference
Coefficients
Scenarios
Optimization model
Cutting planes
Common priors

Keywords

  • Activity based
  • Common prior
  • Goal programming
  • Inverse optimization
  • Mixed integer linear programming
  • Pickup and delivery problem

ASJC Scopus subject areas

  • Management Science and Operations Research
  • Transportation

Cite this

Inverse optimization with endogenous arrival time constraints to calibrate the household activity pattern problem. / Chow, Joseph Ying Jun; Recker, Will W.

In: Transportation Research Part B, Vol. 46, No. 3, 03.2012, p. 463-479.

Research output: Contribution to journalArticle

@article{c2b17c8627d84f6f9155f9a4e4544673,
title = "Inverse optimization with endogenous arrival time constraints to calibrate the household activity pattern problem",
abstract = "A parameter estimation method is proposed for calibrating the household activity pattern problem so that it can be used as a disaggregate, activity-based analog of the traffic assignment problem for activity-based travel forecasting. Inverse optimization is proposed for estimating parameters of the household activity pattern problem such that the observed behavior is optimal, the patterns can be replicated, and the distribution of the parameters is consistent. In order to fit the model to both the sequencing of activities and the arrival times to those activities, an inverse problem is formulated as a mixed integer linear programming problem such that coefficients of the objectives are jointly estimated along with the goal arrival times to the activities. The formulation is designed to be structurally similar to the equivalent problems defined by Ahuja and Orlin and can be solved exactly with a cutting plane algorithm. The concept of a unique invariant common prior is used to regularize the estimation method, and proven to converge using the Method of Successive Averages. The inverse model is tested on sample households from the 2001 California Household Travel Survey and results indicate a significant improvement over the standard inverse problem in the literature as well as baseline prescriptive models that do not make use of sample data for calibration. Although, not unexpectedly, the estimated optimization model by itself is a relatively poor forecasting model, it may be used in determining responses of a population to spatio-temporal scenarios where revealed preference data is absent.",
keywords = "Activity based, Common prior, Goal programming, Inverse optimization, Mixed integer linear programming, Pickup and delivery problem",
author = "Chow, {Joseph Ying Jun} and Recker, {Will W.}",
year = "2012",
month = "3",
doi = "10.1016/j.trb.2011.11.005",
language = "English (US)",
volume = "46",
pages = "463--479",
journal = "Transportation Research, Series B: Methodological",
issn = "0191-2615",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - Inverse optimization with endogenous arrival time constraints to calibrate the household activity pattern problem

AU - Chow, Joseph Ying Jun

AU - Recker, Will W.

PY - 2012/3

Y1 - 2012/3

N2 - A parameter estimation method is proposed for calibrating the household activity pattern problem so that it can be used as a disaggregate, activity-based analog of the traffic assignment problem for activity-based travel forecasting. Inverse optimization is proposed for estimating parameters of the household activity pattern problem such that the observed behavior is optimal, the patterns can be replicated, and the distribution of the parameters is consistent. In order to fit the model to both the sequencing of activities and the arrival times to those activities, an inverse problem is formulated as a mixed integer linear programming problem such that coefficients of the objectives are jointly estimated along with the goal arrival times to the activities. The formulation is designed to be structurally similar to the equivalent problems defined by Ahuja and Orlin and can be solved exactly with a cutting plane algorithm. The concept of a unique invariant common prior is used to regularize the estimation method, and proven to converge using the Method of Successive Averages. The inverse model is tested on sample households from the 2001 California Household Travel Survey and results indicate a significant improvement over the standard inverse problem in the literature as well as baseline prescriptive models that do not make use of sample data for calibration. Although, not unexpectedly, the estimated optimization model by itself is a relatively poor forecasting model, it may be used in determining responses of a population to spatio-temporal scenarios where revealed preference data is absent.

AB - A parameter estimation method is proposed for calibrating the household activity pattern problem so that it can be used as a disaggregate, activity-based analog of the traffic assignment problem for activity-based travel forecasting. Inverse optimization is proposed for estimating parameters of the household activity pattern problem such that the observed behavior is optimal, the patterns can be replicated, and the distribution of the parameters is consistent. In order to fit the model to both the sequencing of activities and the arrival times to those activities, an inverse problem is formulated as a mixed integer linear programming problem such that coefficients of the objectives are jointly estimated along with the goal arrival times to the activities. The formulation is designed to be structurally similar to the equivalent problems defined by Ahuja and Orlin and can be solved exactly with a cutting plane algorithm. The concept of a unique invariant common prior is used to regularize the estimation method, and proven to converge using the Method of Successive Averages. The inverse model is tested on sample households from the 2001 California Household Travel Survey and results indicate a significant improvement over the standard inverse problem in the literature as well as baseline prescriptive models that do not make use of sample data for calibration. Although, not unexpectedly, the estimated optimization model by itself is a relatively poor forecasting model, it may be used in determining responses of a population to spatio-temporal scenarios where revealed preference data is absent.

KW - Activity based

KW - Common prior

KW - Goal programming

KW - Inverse optimization

KW - Mixed integer linear programming

KW - Pickup and delivery problem

UR - http://www.scopus.com/inward/record.url?scp=84856773488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856773488&partnerID=8YFLogxK

U2 - 10.1016/j.trb.2011.11.005

DO - 10.1016/j.trb.2011.11.005

M3 - Article

AN - SCOPUS:84856773488

VL - 46

SP - 463

EP - 479

JO - Transportation Research, Series B: Methodological

JF - Transportation Research, Series B: Methodological

SN - 0191-2615

IS - 3

ER -