Choice modelling in the age of machine learning - Discussion paper

Cranenburgh, Sander van; Wang, Shenhao; Vij, Akshay; Pereira, Francisco C.; Walker, Joan L.

doi:10.1016/j.jocm.2021.100340

Cited by 62 publications

(9 citation statements)

References 145 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The two-step algorithm shows how unsupervised and supervised machine learning methods can work together and interact to improve each other’s performance. The advantages of using machine learning approaches are listed in the following: (i) the structure of the problem is learned from the data as opposed to being predefined; (ii) machine learning is particularly strong at variable selection, unlike statistical approaches where variables are explicitly defined a priori; (iii) machine learning methods are known to have strong predictive power; and (iv) they work well with large datasets ( 20 ). Both bridge and traffic data are used in the calibration of the algorithm.…”

Section: Methodsmentioning

confidence: 99%

Bridge Response and Heavy Truck Classification Framework Based on a Two-Step Machine Learning Algorithm

Mete

Corr

Wilbur

et al. 2021

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Collecting information on heavy trucks and monitoring the bridges which they regularly cross is important for many facets of infrastructure management. In this paper, a two-step algorithm is developed using bridge and truck data, by deploying sequentially unsupervised and supervised machine learning techniques. Longitudinal clustering of bridge data, concerning strain waveforms, is adopted to perform the first step of the algorithm, while image visual inspection and classification tree methods are applied to truck data concurrently in the second step. Both bridge and truck traffic must be monitored for a limited, yet significant, amount of time to calibrate the algorithm, which is then used to build a classification framework. The framework provides the same benefits of two data collection systems while only one needs to be operative. Depending on which monitoring system remains available, the framework enables the use of bridge data to identify the truck’s profile which generated it, or to estimate bridge response given the truck’s information. As a result, the present study aims to provide decision-makers with an effective way to monitor the whole bridge-traffic system, bridge managers to plan effective maintenance, and policymakers to develop ad hoc regulations.

show abstract

Section: Methodsmentioning

confidence: 99%

Bridge Response and Heavy Truck Classification Framework Based on a Two-Step Machine Learning Algorithm

Mete

Corr

Wilbur

et al. 2021

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Discrete choice models (DCMs) relying on full-fledged Natural Language Processing (NLP) methods to make use of additional text data are not yet used in the literature (van Cranenburgh et al 2021). A few papers indicate that both NLP methods and additional text data can capture subtleties that were overlooked in the literature before.…”

Section: Related Workmentioning

confidence: 99%

Moral rhetoric in discrete choice models: a Natural Language Processing approach

2023

Self Cite

View full text Add to dashboard Cite

This paper proposes a new method to combine choice- and text data to infer moral motivations from people’s actions. To do this, we rely on moral rhetoric, in other words, extracting moral values from verbal expressions with Natural Language Processing techniques. We use moral rhetoric based on a well-established moral, psychological theory called Moral Foundations Theory. We use moral rhetoric as input in Discrete Choice Models to gain insights into moral behaviour based on people’s words and actions. We test our method in a case study of voting and party defection in the European Parliament. Our results indicate that moral rhetoric have significant explanatory power in modelling voting behaviour. We interpret the results in the light of political science literature and propose ways for future investigations.

show abstract

“…It would also be of interest to investigate the usefulness of alternative methods, for instance data-driven models such as supervised machine learning methods (see van Cranenburgh et al (2022) for a discussion of current practices of machine learning used for choice modelling). Another interesting option would be to use parts of the dataset for validation and testing, to evaluate out of sample prediction and avoid overfitting, in a similar way to what is common practice in machine learning.…”

Section: Contributions Of Paper 1 and Papermentioning

confidence: 99%

Mode choice modelling of long-distance passenger transport based on mobile phone network data

Andersson

2022

Linköping Studies in Science and Technology. Licentiate Thesis

View full text Add to dashboard Cite

First of all, I would like to thank my main supervisor Maria Börjesson, and my co-supervisors Ida Kristoffersson, Clas Rydergren and Leonid Engelson for their support, clear guidance and honest feedback. I really appreciate you taking the time needed to introduce me to the vast field of transport modelling. The research in this thesis has mainly been funded by the research projects DEMOPAN and DEMOPAN-2 within the research program Transportekonomi at The Swedish Transport Administration. I am grateful to The Swedish Transport Administration to have been given the chance to perform this research. I would also like to thank all my colleagues at both VTI and the division of Communication and Transportation Systems (KTS) at Linköping University. My colleagues at the Transport Economics unit at VTI have helped broaden my understanding of the field of economics, apart from being great fika company as well. My colleagues at Transport Analysis and Logistics at VTI have been supportive and shared their own experiences of transport modelling, as well as their reflections on my research papers throughout the research process. I really appreciate our KTS PhD student online fika sessions, which made it possible to keep my motivation up even during the thoughest restrictions of the pandemic. I would like to give a special thanks to Andrew Daly at the University of Leeds for sharing his extensive experience of logit models. I would also like to give my thanks to the other authors within the DEMOPAN projects who have not yet been mentioned: Nils Breyer and David Gundlegård. Thank you Viveka Nilsson, Andreas Tapani and Magnus Berglund for your administrative support. Last but not least I would like to thank my friends and family, especially my parents Bengt and Helena who have supported me during my research and way before that as well.

show abstract

Choice modelling in the age of machine learning - Discussion paper

Cited by 62 publications

References 145 publications

Bridge Response and Heavy Truck Classification Framework Based on a Two-Step Machine Learning Algorithm

Bridge Response and Heavy Truck Classification Framework Based on a Two-Step Machine Learning Algorithm

Moral rhetoric in discrete choice models: a Natural Language Processing approach

Mode choice modelling of long-distance passenger transport based on mobile phone network data

Contact Info

Product

Resources

About