Research

Background

The transportation of people and freight is ubiquitous and undergoes a transformation that will have tremendous impact on the society, environment and economy. Demand drives this transformation by adopting emerging transport services. This results in integrated transport systems (TS) where the historical separations between private and public transport modes as well between people and freight are blurred. We develop methodologies to predict demand and optimize supply of integrated TS taking the demand response into account. To achieve this objective we develop (i) statistical learning algorithms and (ii) optimization models and solutions methods.

Journal Articles

Submitted, under revision, accepted and published. Students and postdocs are indicated with a star.

Fast Continuous and Integer L-shaped Heuristics Through Supervised Learning

Eric Larsen, Emma Frejinger, Bernard Gendron and Andrea Lodi.

Submitted to INFORMS Journal on Computing in June 2022, under revision.

https://arxiv.org/abs/2205.00897

Reinforcement Learning for Freight Booking Control Problems

Emma Frejinger and Justin Dumouchelle

Submitted to INFORMS Journal on Computing on July 29, 2022.

Optimising Electric Vehicle Charging Station Placement using Advanced Discrete Choice Models

Steven Lamontagne, Margarida Carvalho, Emma Frejinger, Bernard Gendron, Miguel F. Anjos and Ribal Atallah

Submitted to INFORMS Journal on Computing on June 23, 2022.

https://arxiv.org/pdf/2206.11165.pdf

Undiscounted Recursive Path Choice Models: Convergence Properties and Algorithms

Tien Mai and Emma Frejinger

Published in Transportation Science, 56(6):1469-1482, May 2022.

DOI: 10.1287/trsc.2022.1145

The Load Planning and Sequencing Problem for Double-Stack Trains

Mortiz Ruf, Jean-François Cordeau and Emma Frejinger

Published online in Journal of Rail Transport Planning & Management in september, 2022.

DOI: 10.1016/j.jrtpm.2022.100337

A Time-Space Formulation for the Locomotive Routing Problem at the Canadian National Railways

Pedro Miranda, Jean-François Cordeau and Emma Frejinger

Computers and Operations Research, 139: 105629, november 2021.

DOI: 10.1016/j.cor.2021.105629

Routing Policy Choice Prediction in a Stochastic Network: Recursive Model and Solution Algorithm

Tien Mai, Xinlian Yu, Song Gao and Emma Frejinger

Transportation Research Part B, 151: 42-58, July 2021.

DOI: 10.1016/j.trb.2021.06.016

Data-driven Optimization Model Customization

Michael Hewitt and Emma Frejinger

European Journal on Operations Research, 287(2): 438-451, 2020.

DOI: 10.1016/j.ejor.2020.05.010

Integrated Inbound Train Split and Load Planning in an Intermodal Railway Terminal

*Bruno Bruck, Jean-François Cordeau and Emma Frejinger

Transportation Research Part B, 145: 270-289, 2021.

DOI: 10.1016/j.trb.2021.01.006

Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information

*Eric Larsen, *Sébastien Lachapelle, Yoshua Bengio, Emma Frejinger, Simon Lacoste-Julien and Andrea Lodi

INFORMS Journal on Computing, 34(1):227-242, 2022.

DOI: 10.1287/ijoc.2021.1091

The Locomotive Assignment Problem with Distributed Power at the Canadian National Railway Company

*Camilo Ortiz-Astorquiza, Jean-François Cordeau and Emma Frejinger

Transportation Science. 55(2): 275-552, 2021.

A tutorial on recursive models for analyzing and predicting path choice behavior

*Maëlle Zimmermann and Emma Frejinger

Accepted for publication in the EURO Journal on Transportation and Logistics on December 3, 2019.

DOI: https://doi.org/10.1016/j.ejtl.2020.100004

A Strategic Markovian Traffic Equilibrium Model for Capacitated Networks

*Maëlle Zimmermann, Emma Frejinger and Patrice Marcotte

Transportation Science. Volume: 55, Number: 3 (May-June 2021): 574-591.

DOI: https://doi.org/10.1287/trsc.2020.1033

Route choice behavior and travel information in a congested network: Static and dynamic recursive models

*Giselle De Moraes Ramos, *Tien Mai, Winnie Daamen, Emma Frejinger and Serge Hoogendoorn

Transportation Research Part C: Emerging Technologies 114: 681-693, 2020.

DOI: https://doi.org/10.1016/j.trc.2020.02.014

An empirical study on aggregation of alternatives and its influence on prediction in car type choice models

*Shiva Habibi, Emma Frejinger and Markus Sundberg

Transportation 46(3): 563-582, 2019.

DOI: https://doi.org/10.1007/s11116-017-9828-5

The Load Planning Problem for Double-Stack Intermodal Trains

*Serena Mantovani, *Gianluca Morganti, *Nitish Umang, Teodor Gabriel Crainic, Emma Frejinger and *Eric Larsen

European Journal of Operations Research 267(1): 107-119, 2018.

DOI: https://doi.org/10.1016/j.ejor.2017.11.016

A decomposition method for estimating recursive logit based route choice models

*Tien Mai, Fabian Bastin and Emma Frejinger

EURO Journal on Transportation and Logistics 7(3):253-275, 2018.

DOI: https://doi.org/10.1016/j.ejtl.2020.100004

Capturing correlation with a mixed recursive logit model for activity-travel scheduling

*Maëlle Zimmermann, *Oscar Blom Västberg, Emma Frejinger and Anders Karlström

Transportation Research Part C: Emerging Technologies 93: 273-291, 2018.

DOI: https://doi.org/10.1016/j.trc.2018.05.032

A dynamic programming approach for quickly estimating large network-based MEV models

*Tien Mai, Emma Frejinger, Mogens Fosgerau and Fabian Bastin

Transportation Research Part B 98(1): 179-197, 2017.

DOI: https://doi.org/10.1016/j.trb.2016.12.017

Bike route choice modelling using GPS data without choice sets of paths

*Maëlle Zimmermann, *Tien Mai and Emma Frejinger

Transportation Research Part C 75(1): 183-196, 2017.

DOI: https://doi.org/10.1016/j.trc.2016.12.009

On the similarities between random regret minimization and mother logit : The case of recursive route choice models

*Tien Mai, Fabian Bastin and Emma Frejinger

Journal of Choice Modelling 23(1): 21-33, 2017.

DOI: https://doi.org/10.1016/j.jocm.2017.03.002

A misspecification test for logit-based route choice models

*Tien Mai, Emma Frejinger and Fabian Bastin

Economics of Transportation. 4(4): 215-226, 2015.

DOI: https://doi.org/10.1016/j.ecotra.2015.08.002

A nested recursive logit model for route choice analysis

*Tien Mai, Mogens Fosgerau and Emma Frejinger

Transportation Research Part B 75(1): 100-112, 2015.

DOI: https://doi.org/10.1016/j.trb.2015.03.015

A link-based network route choice model with unrestricted choice set

Mogens Fosgerau, Emma Frejinger and Anders Karlstöm

Transportation Research Part B 56(1): 70-80, 2013.

DOI: https://doi.org/10.1016/j.trb.2013.07.012

Cognitive Cost in Route Choice with Real-Time Traffic Information: An Exploratory Analysis

Song Gao, Emma Frejinger and Moshe Ben-Akiva

Transportation Research Part A 45(9): 916-926, 2011.

DOI: https://doi.org/10.1016/j.sbspro.2011.04.511

Adaptive route choices in risky traffic networks: A prospect theory approach

Song Gao, Emma Frejinger and Moshe Ben-Akiva

Transportation Research Part C 18(5): 727-740, 2010.

DOI: https://doi.org/10.1016/j.trc.2009.08.001

Sampling of alternatives for route choice modeling

Emma Frejinger, Michel Bierlaire and Moshe Ben-Akiva

Transportation Research Part B 43(10): 984-994, 2009.

DOI: https://doi.org/10.1016/j.trb.2009.03.001

Adaptive Route Choice Models in Stochastic Time-Dependent networks

Song Gao, Emma Frejinger and Moshe Ben-Akiva

Transportation Research Record 2085: 136-143, 2008.

DOI: https://doi.org/10.3141/2085-15

Route choice modeling with network-free data

Michel Bierlaire and Emma Frejinger

Transportation Research Part C 16(2): 187-198, 2008.

DOI: https://doi.org/10.1016/j.trc.2007.07.007

Capturing correlation with subnetworks in route choice models

Emma Frejinger and Michel Bierlaire

Transportation Research Part B 41(3): 363-378, 2007.

DOI: https://doi.org/10.1016/j.trb.2006.06.003

Research: Publications

Conference Proceedings

A learning-based algorithm to quickly compute good primal solutions for Stochastic Integer Programs

Yoshua Bengio, Emma Frejinger, Andrea Lodi, *Rahul Patel and *Sriram Sankaranarayanan

Seventeenth International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR). Accepted for publication, 2020.

arXiv:1912.08112

Block planning for intermodal rail: methodology and case study

*Gianluca Morganti, Teodor Gabriel Crainic, Emma Frejinger and Nicoletta Ricciardi

Published in Transportation Research Procedia 47, 19–26, 2020.

https://doi.org/10.1016/j.trpro.2020.03.068

Research: Publications

Software

RECURSIVE LOGIT ESTIMATION

PDF Presentation

Code

Research: Text

Research

Background

Journal Articles

​Fast Continuous and Integer L-shaped Heuristics Through Supervised Learning

Reinforcement Learning for Freight Booking Control Problems

Optimising Electric Vehicle Charging Station Placement using Advanced Discrete Choice Models

Undiscounted Recursive Path Choice Models: Convergence Properties and Algorithms

The Load Planning and Sequencing Problem for Double-Stack Trains

A Time-Space Formulation for the Locomotive Routing Problem at the Canadian National Railways

Routing Policy Choice Prediction in a Stochastic Network: Recursive Model and Solution Algorithm

Data-driven Optimization Model Customization

Integrated Inbound Train Split and Load Planning in an Intermodal Railway Terminal

Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information

The Locomotive Assignment Problem with Distributed Power at the Canadian National Railway Company

A tutorial on recursive models for analyzing and predicting path choice behavior

A Strategic Markovian Traffic Equilibrium Model for Capacitated Networks

Route choice behavior and travel information in a congested network: Static and dynamic recursive models

An empirical study on aggregation of alternatives and its influence on prediction in car type choice models

The Load Planning Problem for Double-Stack Intermodal Trains

A decomposition method for estimating recursive logit based route choice models

Capturing correlation with a mixed recursive logit model for activity-travel scheduling

A dynamic programming approach for quickly estimating large network-based MEV models

Bike route choice modelling using GPS data without choice sets of paths

On the similarities between random regret minimization and mother logit : The case of recursive route choice models

A misspecification test for logit-based route choice models

A nested recursive logit model for route choice analysis

A link-based network route choice model with unrestricted choice set

Cognitive Cost in Route Choice with Real-Time Traffic Information: An Exploratory Analysis

Adaptive route choices in risky traffic networks: A prospect theory approach

Sampling of alternatives for route choice modeling

Adaptive Route Choice Models in Stochastic Time-Dependent networks

Route choice modeling with network-free data

Capturing correlation with subnetworks in route choice models

Conference Proceedings

A learning-based algorithm to quickly compute good primal solutions for Stochastic Integer Programs

Block planning for intermodal rail: methodology and case study

Software

Fast Continuous and Integer L-shaped Heuristics Through Supervised Learning