Abstract

. This study applies experimental methods to analyze travel mode choice. Two different scenarios are considered. In the first scenario, subjects have to decide whether to commute by car or by metro. Metro costs are fixed, while car costs are uncertain and determined by the joint effect of casual events and traffic congestion. In the second scenario, subjects have to decide whether to travel by car or by bus, both modes in which costs are determined by the combination of chance and congestion. Subjects receive feedback information on the actual travel times of both modes. We find that individuals exhibit a marked preference for cars, are inclined to confirm their first choice and demonstrate travel mode stickiness. We conclude that travel mode choice is subject to heuristics and biases that lead to robust deviations from rational choice.

Abstract

Data analysis plays a key role in supporting the development of sustainable transportation. Using the large-scale household mobility survey data collected in Milan, Italy during 2005–2006, we study whether the large-scale data contribute to improving accuracy in estimating household travel modes. This paper presents three machine learning methods including multinomial logit (MNL) model, random forest (RF) and support vector machine (SVM) to estimate the household travel mode. Their model accuracies are 70.41%, 71.89%, 72.74% respectively under the full sample size. It is found that the accuracies of these three methods fluctuate fiercely when the sample size is less than 20,000 and then stabilize gradually with continuous increasing it. After stabilization occurs, accuracies with these three methods do not significantly increase as the sample size continues to increase. We also study the travel characteristics derived from the large-scale survey data, which is fundamental for developing a sustainable transportation system. The collected data items include five explanatory variables, i.e., household size (HS), vehicle ownership, household income (HI), travel distance, travel time and one response variable (i.e., household travel mode), which includes public transport (PT), private car, usage of PT and private car simultaneously and the others travel modes (e.g., walk). We further investigate the importance of explanatory variables in terms of estimating household travel mode choice with the MNL model. It is found that vehicle ownership is the most critical factor influencing household travel mode choice, followed by travel distance, travel time, HS and HI. The ranking result is consistent with the RF approach.

Abstract

In many big cities, the bike-sharing system (BSS) and taxi play critical roles in transportation services. They both offer on-demand transportation options and allow flexible riding scheduling and routing. Previous literature has compared BSS and taxi to other transport modes, such as public transit and private automobile, but little is known about the spatiotemporal factors that influence travel choices between these two alternatives. Understanding travel patterns of BSS and taxi is critical in traffic demand analysis and sustainable transportation planning. Also, an in-depth examination of the patterns of travel behaviors, especially when one would choose BSS over a taxi, will provide valuable insights on human mobility and active living research. In this study, we investigated the spatiotemporal patterns of BSS and taxi trips in Chicago from 2014 to 2016. To model travel choices between BSS and taxi, we applied machine learning techniques to simulate the means of transport based on environmental and temporal factors. Results show seasonal trip variations of the BSS and a declining trend of taxi trips. BSS speed is relatively stable while taxi speed varies primarily because of time and locations. Based on the random forest model, which has demonstrated the best fit with high processing speed, travel distance and the number of parks and recreational facilities seem to be critical spatial predicting factors of the travel choice. Given any time and location, the model can recommend the travel choices between BSS and taxis for users. This study shows the significance of machine learning techniques in urban mobility research. Results of the study may potentially support people's transportation decision-making and facilitate sustainable transportation planning.