Application of Bayesian stochastic learning automata for modeling lane choice behavior on high-occupancy toll lanes on State Road 167

Ender Faruk Morgül, Kaan Ozbay, Abdullah Kurkcu

Research output: Contribution to journalArticle

Abstract

This paper investigates the learning behavior of users of State Road 167 high-occupancy toll lanes by use of toll transaction data collected over a 6-month period. The Bayesian stochastic learning algorithm theory was used to model drivers' sequential lane choice decisions. Reward and penalty parameters were used to update users' lane choice probabilities. The results showed that the effect of reward parameters that increased the probability of selection of an alternative after a satisfactory experience was more obvious than the effect of penalty parameters that decreased the probability of selection of an unfavorable choice. Low magnitudes of learning parameters might indicate strong habit formation of users. Moreover, the posterior distributions of learning parameters indicated that user perception heterogeneity existed when the outcomes of choices were evaluated. Finally, user familiarity was investigated with a subsample of less experienced users, and it was shown that the learning rates of more familiar users were lower than those of less familiar users.

Original languageEnglish (US)
Pages (from-to)97-107
Number of pages11
JournalTransportation Research Record
Volume2560
DOIs
StatePublished - 2016

Fingerprint

Learning algorithms

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

Application of Bayesian stochastic learning automata for modeling lane choice behavior on high-occupancy toll lanes on State Road 167. / Morgül, Ender Faruk; Ozbay, Kaan; Kurkcu, Abdullah.

In: Transportation Research Record, Vol. 2560, 2016, p. 97-107.

Research output: Contribution to journalArticle

@article{2fdd56a178a546b68f7cb4f96491a11f,
title = "Application of Bayesian stochastic learning automata for modeling lane choice behavior on high-occupancy toll lanes on State Road 167",
abstract = "This paper investigates the learning behavior of users of State Road 167 high-occupancy toll lanes by use of toll transaction data collected over a 6-month period. The Bayesian stochastic learning algorithm theory was used to model drivers' sequential lane choice decisions. Reward and penalty parameters were used to update users' lane choice probabilities. The results showed that the effect of reward parameters that increased the probability of selection of an alternative after a satisfactory experience was more obvious than the effect of penalty parameters that decreased the probability of selection of an unfavorable choice. Low magnitudes of learning parameters might indicate strong habit formation of users. Moreover, the posterior distributions of learning parameters indicated that user perception heterogeneity existed when the outcomes of choices were evaluated. Finally, user familiarity was investigated with a subsample of less experienced users, and it was shown that the learning rates of more familiar users were lower than those of less familiar users.",
author = "Morg{\"u}l, {Ender Faruk} and Kaan Ozbay and Abdullah Kurkcu",
year = "2016",
doi = "10.3141/2560-11",
language = "English (US)",
volume = "2560",
pages = "97--107",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",

}

TY - JOUR

T1 - Application of Bayesian stochastic learning automata for modeling lane choice behavior on high-occupancy toll lanes on State Road 167

AU - Morgül, Ender Faruk

AU - Ozbay, Kaan

AU - Kurkcu, Abdullah

PY - 2016

Y1 - 2016

N2 - This paper investigates the learning behavior of users of State Road 167 high-occupancy toll lanes by use of toll transaction data collected over a 6-month period. The Bayesian stochastic learning algorithm theory was used to model drivers' sequential lane choice decisions. Reward and penalty parameters were used to update users' lane choice probabilities. The results showed that the effect of reward parameters that increased the probability of selection of an alternative after a satisfactory experience was more obvious than the effect of penalty parameters that decreased the probability of selection of an unfavorable choice. Low magnitudes of learning parameters might indicate strong habit formation of users. Moreover, the posterior distributions of learning parameters indicated that user perception heterogeneity existed when the outcomes of choices were evaluated. Finally, user familiarity was investigated with a subsample of less experienced users, and it was shown that the learning rates of more familiar users were lower than those of less familiar users.

AB - This paper investigates the learning behavior of users of State Road 167 high-occupancy toll lanes by use of toll transaction data collected over a 6-month period. The Bayesian stochastic learning algorithm theory was used to model drivers' sequential lane choice decisions. Reward and penalty parameters were used to update users' lane choice probabilities. The results showed that the effect of reward parameters that increased the probability of selection of an alternative after a satisfactory experience was more obvious than the effect of penalty parameters that decreased the probability of selection of an unfavorable choice. Low magnitudes of learning parameters might indicate strong habit formation of users. Moreover, the posterior distributions of learning parameters indicated that user perception heterogeneity existed when the outcomes of choices were evaluated. Finally, user familiarity was investigated with a subsample of less experienced users, and it was shown that the learning rates of more familiar users were lower than those of less familiar users.

UR - http://www.scopus.com/inward/record.url?scp=85015441157&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015441157&partnerID=8YFLogxK

U2 - 10.3141/2560-11

DO - 10.3141/2560-11

M3 - Article

AN - SCOPUS:85015441157

VL - 2560

SP - 97

EP - 107

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

ER -