Capturing the conditions that introduce systematic variation in bike-sharing travel behavior using data mining techniques

Bordagaray, María Eugenia; dell’Olio, Luigi; Fonzone, Achille; Ibeas, Ángel

doi:10.1016/j.trc.2016.07.009

Cited by 86 publications

(41 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The average trip distances for matched and unmatched public bicycle SC data are 0.95 km and 1.03 km, respectively, indicating the distance of first-mile or last-mile public bicycle trips is shorter than that of the other public bicycle trips. In contrast, the average trip distance is 0.99 km in Santander, Spain [24]. Notably, unmatched public bicycle SC data also contains first-mile or last-mile trips to connect metro.…”

Section: Results and Validationmentioning

confidence: 99%

See 1 more Smart Citation

An Association Rule Based Method to Integrate Metro-Public Bicycle Smart Card Data for Trip Chain Analysis

Zhao

Wang

Ong

et al. 2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

Smart card data provide valuable insights and massive samples for enhancing the understanding of transfer behavior between metro and public bicycle. However, smart cards for metro and public bicycle are often issued and managed by independent companies and this results in the same commuter having different identity tags in the metro and public bicycle smart card systems. The primary objective of this study is to develop a data fusion methodology for matching metro and public bicycle smart cards for the same commuter using historical smart card data. A novel method with association rules to match the data derived from the two systems is proposed and validation was performed. The results showed that our proposed method successfully matched 573 pairs of smart cards with an accuracy of 100%. We also validated the association rules method through visualization of individual metro and public bicycle trips. Based on the matched cards, interesting findings of metro-bicycle transfer have been derived, including the spatial pattern of the public bicycle as first/last mile solution as well as the duration of a metro trip chain.

show abstract

Section: Results and Validationmentioning

confidence: 99%

“…By far, public bicycle SC data has been used to investigate public bicycle users' travel patterns [22] as well as bicycle trip chains for men and women [14,23]. Public bicycle SC data could also help to classify different types of behaviors and compare the trip disparity [24].…”

Section: Smart Card Data For Trip Chainmentioning

confidence: 99%

An Association Rule Based Method to Integrate Metro-Public Bicycle Smart Card Data for Trip Chain Analysis

Zhao

Wang

Ong

et al. 2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…With the development of the emerging sharing economy, bike-sharing services are increasingly attracting the attention of researchers, policy makers, and social marketers [19,20]. Existing studies have mainly analyzed the travel characteristics based on travel speed and travel time [21,22] and the purpose of shared bicycle travel [23], or studied the impact of gender on travel behavior based on visualization technology [24]. These studies are mainly based on movement and ignore the transitional activities between successive trips in the travel chain.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Bad weather, Light traffic period, Commuting travel, Long-distance (>10 km) 22 Bad weather, Light traffic period, Other travel, Short-distance (<3 km) 23 Bad weather, Light traffic period, Other travel, Medium-distance (3-10 km) 24 Bad weather, Light traffic period, Other travel, Long-distance (>10 km) Figure 1. The number of respondents using bike-sharing in a week.…”

Section: Hypothetical Scenariosmentioning

confidence: 99%

Mixed Logit Models for Travelers’ Mode Shifting Considering Bike-Sharing

Chen

Yang³

et al. 2020

Sustainability

View full text Add to dashboard Cite

This study quantifies the impact of individual attributes, the built environment, and travel characteristics on the use of bike-sharing and the willingness of shifting to bike-sharing-related travel modes (bike-sharing combined with other public transportation modes such as bus and subway) under different scenarios. The data are from an RP (Revealed Preference) survey and SP (Stated Preference) survey in Nanjing, China. Three mixed logit models are established: an individual attribute–travel characteristics model, a various-factor bike-sharing usage frequency model, and a mixed scenario–transfer willingness model. It is found that age and income are negatively associated with bike-sharing usage; the transfer distance (about 1 km), owning no car, students, and enterprises are positively associated with bike-sharing usage; both weather and travel distance have a significant negative impact on mode shifting. The sesearch conclusions can provide a reference for the formulation of urban transportation policies, the daily operation scheduling, and service optimization of bike-sharing.

show abstract

“…Maria Bordagaray proposed a data mining algorithm to analyze the bike usage casuistry within a sharing scheme. The proposed algorithm is a powerful tool to characterize the actual demand for bike-sharing systems [7]. Leonardo Caggiania et al proposed a comprehensive dynamic bike redistribution method.…”

Section: Literature Review Of Bike-sharing Demand Related Studiesmentioning

confidence: 99%

Controlling the blind expansion of dockless shared bicycles through travel demand identification and prediction

Wang¹,

Yuan²,

Wang³

2019

World Congress on Civil, Structural, and Environmental Engineering

View full text Add to dashboard Cite

Free-floating bike sharing (FFBS) is an innovative bike sharing mode that is expanding rapidly around the world nowadays. FFBS has always been known to significantly reduce traffic congestion, urban traffic carbon emissions, noise, and support a greener sustainable development of urban environments. However, without knowing the users' travel demand locations and quantity, blindly expanding shared bicycles on the market has already caused shared bicycle "disasters" which affect city environment and cause serious waste of resources in some Chinese cities. This paper proposes a mid-long term FBBS travel demand identification and prediction methodology which is an important support for bike-sharing companies' in determining the number of shared bicycles' deployment and avoid blind expansion. The methodology first uses a spatial-temporal trajectory clustering algorithm based on an innovative spatialtemporal distance function. By clustering individual users' long-term travel trajectories, the regular travel demand and random demand can be identified. Then, the total demand to be known of a future period is determined by the sum of two parts, total regular demand based on aggregated individual regularities and total random demand predicted based on a proposed MLP Neural Net Model. At last, the proposed methodology is tested using a two weeks' dataset of shared bicycle travel trajectories from Beijing Mobike system. The results indicate that the proposed methodology based on regular travel identification and prediction has strong practicability and outperforms the method directly using total demand to predict in terms of accuracy.

show abstract

Capturing the conditions that introduce systematic variation in bike-sharing travel behavior using data mining techniques

Cited by 86 publications

References 35 publications

An Association Rule Based Method to Integrate Metro-Public Bicycle Smart Card Data for Trip Chain Analysis

An Association Rule Based Method to Integrate Metro-Public Bicycle Smart Card Data for Trip Chain Analysis

Mixed Logit Models for Travelers’ Mode Shifting Considering Bike-Sharing

Controlling the blind expansion of dockless shared bicycles through travel demand identification and prediction

Contact Info

Product

Resources

About