Competitive Mode Choice Behavior between E-Bike and Bike Based on Discrete Choice Model

2009 ◽  
Author(s):  
Min He ◽  
Mingwei He ◽  
Ren Dong ◽  
Yan Hou
Keyword(s):  
Discrete Choice ◽  
Choice Behavior ◽  
Choice Model ◽  
Mode Choice ◽  
Discrete Choice Model

Travel Mode Choice Modeling: Predictive Efficacy between Machine Learning Models and Discrete Choice Model

2021 ◽  
Vol 15 (1) ◽  
pp. 241-255
Author(s):  
Nur Fahriza Mohd. Ali ◽  
Ahmad Farhan Mohd. Sadullah ◽  
Anwar PP Abdul Majeed ◽  
Mohd Azraai Mohd. Razman ◽  
Muhammad Aizzat Zakaria ◽  
...  
Keyword(s):  
Machine Learning ◽  
Discrete Choice ◽  
Choice Model ◽  
Mode Choice ◽  
Binary Logistic Regression ◽  
Discrete Choice Model ◽  
Learning Models ◽  
Travel Mode ◽  
Travel Mode Choice ◽  
Machine Learning Models

Background: A complex travel behaviour among users is intertwined with many factors. Traditionally, the exploration in travel mode choice modeling has been dominated by the Discrete Choice model, nonetheless, owing to the advancement in computational techniques, machine learning has gained traction in understanding travel behavior. Aim: This study aims at predicting users’ travel model choice by means of machine learning models against a conventional Discrete Choice Model, i.e., Binary Logistic Regression. Objective: To investigate the comparison between machine learning models, namely Neural Network, Random Forest, Decision Tree, and Support Vector Machine against the Discrete Choice Model (Binary Logistic Regression) in the prediction of travel mode choice amongst Kuantan City. Methodology: The dataset was collected in Kuantan City, Malaysia, through the Revealed/Stated Preferences (RP/SP) Survey. The data collected was split into a ratio of 80:20 for training and testing before evaluating them between the aforesaid models. The hyperparameters of the models were set to default. The performance of the models is evaluated based on classification accuracy. Results: It was shown in the present study that the Neural Network Model is able to attain a higher prediction accuracy as compared to Binary Logistic Regression (Discrete Choice Model) in classifying mode choice of Kuantan users either to choose public transport or private vehicles as daily transportation. Feature importance technique is crucial for identifying the significant features in modelling travel mode choice. It is demonstrated that the Neural Network Model can yield exceptional classification of mode choice up to 73.4% and 72.4% of training and testing data, respectively, by considering the features identified via the feature importance technique, suggesting the viability of the proposed technique in supporting an informed decision. Conclusion: The findings highlight the strengths and limitations of the Machine Learning Technique as well as the Discrete Choice Model in modeling travel mode choice. It was shown that Machine Learning models have the capability to provide better prediction that could assist the urban transportation planning among policymakers. Meanwhile, it could be also demonstrated that the Discrete Choice Model (Binary Logistic Regression) is helpful in getting a better understanding in expressing the inference relationship between variables for improvising the future transportation system.

Measuring the Impact of Latent Variables on Mode Choice Behavior between Bike and Electric Bike

2011 ◽  
Vol 255-260 ◽  
pp. 4075-4079
Author(s):  
Ming Wei He ◽  
Min He ◽  
Xiao Qing Yang ◽  
Qing Qian Zhao
Keyword(s):  
Discrete Choice ◽  
Latent Variables ◽  
Choice Behavior ◽  
Choice Model ◽  
Mode Choice ◽  
Traffic Planning ◽  
Taste Heterogeneity ◽  
The Impact ◽  
Electric Bike ◽  
Sampling Survey

The researches on competitive mode choice behavior between electric bike and bike are useful for the analysis and forecasting of traffic mode, non-motorized traffic planning and related policy. With the sampling survey data in Kunming, individuals’ attitude and preference are analyzed based on SP data. The competitive choice model between electric bike and bike based on discrete choice model is established. The impact of latent variables on mode choice behavior between bike and electric bike is measured based on the estimation results. The result shows that the latent variables have significant impact on the choice behavior. The latent variables can be used to improve the performance of the model and to better capture taste heterogeneity.

Mode Choice Behavior Analysis by Using a Semi-Compensatory Discrete Choice Model

2013 ◽  
Vol 838-841 ◽  
pp. 3300-3304
Author(s):  
Chong Wei ◽  
Lin Xiao ◽  
Chun Fu Shao
Keyword(s):  
Discrete Choice ◽  
Posterior Distribution ◽  
Choice Behavior ◽  
Data Augmentation ◽  
Choice Model ◽  
Mode Choice ◽  
Estimation Procedure ◽  
Bayes Theorem ◽  
Proposed Model ◽  
Conjunctive Rule

In this study we proposed a semi-compensatory model to analyze the mode choice behavior. The proposed model formulated the conjunctive rule through a straightforward way. The proposed model can take into account the probability distribution of the threshold involved by the conjunctive rule. To estimate the parameters of the proposed model, we derived the posterior distribution of the parameters by using the Bayes theorem and developed a blacked Metropolis-Hastings algorithm to carry out the estimation based on the posterior distribution. We also employed the data augmentation technology to simplify the estimation procedure. The proposed model was validated by using a SP survey dataset. We compared the performance of the proposed model to that of the logit model.

Discrete choice model for air-cargo mode selection

2014 ◽  
Vol 25 (3) ◽  
pp. 656-672 ◽  
Author(s):  
Subhro Mitra ◽  
Steven M. Leon
Keyword(s):  
Discrete Choice ◽  
Choice Model ◽  
Mode Choice ◽  
Mode Selection ◽  
Discrete Choice Model ◽  
Air Cargo ◽  
Demand Forecast ◽  
Content Type ◽  
Preference Data ◽  
Factors Influencing

Purpose – The purpose of this paper is to develop a better understanding of the factors that influence a shipper's decision to choose air cargo as a mode of shipment. Design/methodology/approach – A disaggregate multinomial discrete choice model is developed using freight shipment survey data to identify critical factors influencing air cargo mode choice. Disaggregate revealed preference data is obtained from surveying 347 manufacturers, freight forwarders, and other third-party service providers. Findings – The empirical model developed in this research shows that the rate of shipment, time of transit, cost-per-pound shipped, quantity shipped, perishability and delay rate of the mode are significant factors that influence mode choice. Research limitations/implications – The discrete choice model developed can be improved by taking into account logistics costs not considered in this research. Perhaps more in-depth surveys of the shippers and freight forwarders are needed. Additionally, improving the mode choice model by including stated preference data and subsequently incorporating service quality latent variables would be beneficial. Practical implications – Identifying the sensitivity of the shippers to various factors influencing mode selection enables transportation planners make better demand forecast for each mode of transportation. Originality/value – This paper extends previous mode choice studies by analyzing mode selection between air cargo and other modes. Better forecasting is achieved by replacing the logit model with probit, heteroscedastic extreme value and mixed logit models.

The Impact of Zoning and Built Environment Characteristics on Transit, Biking, and Walking

2019 ◽  
Vol 11 (1) ◽  
pp. 108-129
Author(s):  
Andrew G. Mueller ◽  
Daniel J. Trujillo
Keyword(s):  
Land Use ◽  
Built Environment ◽  
Discrete Choice ◽  
Travel Behavior ◽  
Choice Model ◽  
Mode Choice ◽  
Land Use Regulation ◽  
Policy Action ◽  
Development Goals ◽  
The Impact

This study furthers existing research on the link between the built environment and travel behavior, particularly mode choice (auto, transit, biking, walking). While researchers have studied built environment characteristics and their impact on mode choice, none have attempted to measure the impact of zoning on travel behavior. By testing the impact of land use regulation in the form of zoning restrictions on travel behavior, this study expands the literature by incorporating an additional variable that can be changed through public policy action and may help cities promote sustainable real estate development goals. Using a unique, high-resolution travel survey dataset from Denver, Colorado, we develop a multinomial discrete choice model that addresses unobserved travel preferences by incorporating sociodemographic, built environment, and land use restriction variables. The results suggest that zoning can be tailored by cities to encourage reductions in auto usage, furthering sustainability goals in transportation.

Sign in / Sign up

Export Citation Format

Share Document