E-scooter sharing programs have transformed urban mobility, providing an environmentally friendly solution for short-distance travel. Analyzing Origin-Destination (OD) travel behavior associated with e-scooter trip patterns is essential for effective urban planning, infrastructure enhancement, and policymaking. However, while numerous studies exist on developing OD travel behavior for passenger vehicles, there is a significant gap in developing such models for shared transportation modes like e-scooters. This study addresses this gap by estimating an OD model for e-scooter trips, integrating Points of Interest data from Yelp. E-scooter mobility data, traffic analysis zone (TAZ) shapefiles, and crowdsourced data from Louisville, KY, were collected to develop the OD model. Using a gravity-inspired random forest (RF) model, the e-scooter OD trip model was estimated. Findings revealed that total attraction and production have a high positive influence on trip distribution between TAZ, while the distance between TAZ has a significant negative impact. Additionally, the presence of bars, restaurants, shopping malls, and coffee shops strongly influences trip distribution between TAZ, whereas museums and parks have less influence. These results offer valuable insights for planning organizations, informing decisions on the relocation and optimization of e-scooter services to better meet the needs of urban commuters.
AntoniouCBalakrishnaRKoutsopoulosHN (2011) A synthesis of emerging data collection technologies and their impact on traffic management applications. European Transport Research Review3: 139–148.
2.
BaekKLeeHChungJ-H, et al. (2021) Electric scooter sharing: how do people value it as a last-mile transportation mode?Transportation Research Part D: Transport and Environment90: 102642.
3.
BishopCMNasrabadiNM (2006) Pattern Recognition and Machine Learning. Springer.
4.
BreimanL (2001) Random forests. Machine Learning45: 5–32.
5.
CaspiOSmartMJNolandRB (2020) Spatial associations of dockless shared e-scooter usage. Transportation Research Part D: Transport and Environment86: 102396.
6.
CubellsJMiralles-GuaschCMarquetO (2023) E-scooter and bike-share route choice and detours: modelling the influence of built environment and sociodemographic factors. Journal of Transport Geography111: 103664.
7.
DasPR (2021) Internal Consistency Of Pro Environmental Attitude Questionnaire Items. Kolkata: Indian Statistical Institute.
8.
Di ClementeRLuengo-OrozMTravizanoM, et al. (2018) Sequences of purchases in credit card data reveal lifestyles in urban populations. Nature Communications9: 3330.
9.
GuoZLiuJZhaoP, et al. (2023) Spatiotemporal heterogeneity of the shared e-scooter–public transport relationships in Stockholm and Helsinki. Transportation Research Part D: Transport and Environment122: 103880.
10.
HamSWChoJ-HParkS, et al. (2021) Spatiotemporal demand prediction model for e-scooter sharing services with latent feature and deep learning. Transportation Research Record: Journal of the Transportation Research Board2675: 34–43.
11.
HardinJWHilbeJM (2007) Generalized Linear Models and Extensions. Stata press.
12.
HeSShinKG (2020) Dynamic flow distribution prediction for urban dockless e-scooter sharing reconfiguration. In: Proceedings of the Web Conference 2020, 133–143.
13.
HosseinzadehAKarimpourAKlugerR (2021) Factors influencing shared micromobility services: an analysis of e-scooters and bikeshare. Transportation Research Part D: Transport and Environment100: 103047.
14.
HussainEBhaskarAChungE (2021) A novel origin destination based transit supply index: exploiting the opportunities with big transit data. Journal of Transport Geography93: 103040.
15.
IsardW (2017) Gravity and spatial interaction models. In: Methods of Interregional and Regional Analysis. Routledge, 243–280.
16.
JamesGWittenDHastieT, et al. (2013) An Introduction to Statistical Learning. Springer.
17.
JanitzaSHornungR (2018) On the overestimation of random forest’s out-of-bag error. PLoS One13: e0201904.
18.
JiaoJDegenNAzimianA (2022) Understanding the relationships among E-scooter ridership, transit desert index, and health-related factors. Transportation Research Record: 03611981221097094.
19.
JolliffeIT (2002) Principal Component Analysis for Special Types of Data. Springer.
20.
KarimpourAHosseinzadehAKlugerR (2023) A data-driven approach to estimating dockless electric scooter service areas. Journal of Transport Geography109: 103579.
21.
KimSChooSLeeG, et al. (2022) Predicting demand for shared e-scooter using community structure and deep learning method. Sustainability14: 2564.
22.
KimptonALoginovaJPojaniD, et al. (2022) Weather to scoot? How weather shapes shared e-scooter ridership patterns. Journal of Transport Geography104: 103439.
23.
LeeMChowJYYoonG, et al. (2021) Forecasting e-scooter substitution of direct and access trips by mode and distance. Transportation Research Part D: Transport and Environment96: 102892.
24.
LiawAWienerM (2002) Classification and regression by randomForest. R News2: 18–22.
25.
LiuMSeederSLiH (2019) Analysis of e-scooter trips and their temporal usage patterns. Institute of Transportation Engineers. ITE Journal89: 44–49.
26.
LOJIC (2019) The louisville/jefferson county information consortium. Available at: https://www.lojic.org/
27.
MathewJKLiuMBullockDM (2019) Impact of weather on shared electric scooter utilization. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC). IEEE, 4512–4516.
28.
MerlinLAYanXXuY, et al. (2021) A segment-level model of shared, electric scooter origins and destinations. Transportation Research Part D: Transport and Environment92: 102709.
29.
MoosaviSMHMaZArmaghaniDJ, et al. (2022) Understanding and predicting the usage of shared electric scooter services on university campuses. Applied Sciences12: 9392.
30.
MunizagaMDevillaineFNavarreteC, et al. (2014) Validating travel behavior estimated from smartcard data. Transportation Research Part C: Emerging Technologies44: 70–79.
31.
OrvinMMBachhalJKFatmiMR (2022) Modeling the demand for shared e-scooter services. Transportation Research Record: Journal of the Transportation Research Board2676: 429–442.
32.
PearsonK (1895) VII. Note on regression and inheritance in the case of two parents. Proceedings of the Royal Society of London58: 240–242.
33.
PhithakkitnukooonSPatanukhomKDemissieMG (2021) Predicting spatiotemporal demand of dockless e-scooter sharing services with a masked fully convolutional network. ISPRS International Journal of Geo-Information10: 773.
34.
ReckDJGuidonSAxhausenKW (2021) Modelling shared e-scooters: a spatial regression approach. In: 9th Symposium of the European Association for Research in Transportation (hEART 2020). European Association for Research in Transportation.
35.
ShahNRGuoJHanLD, et al. (2023) Why do people take e-scooter trips? Insights on temporal and spatial usage patterns of detailed trip data. Transportation Research Part A: Policy and Practice173: 103705.
36.
SmithLI (2002) A tutorial on principal components analysis.
37.
SongJ-CHsiehI-YLChenC-S (2023) Sparse trip demand prediction for shared E-scooter using spatio-temporal graph neural networks. Transportation Research Part D: Transport and Environment125: 103962.
38.
TerolRMReinaARZiaeiS, et al. (2020) A machine learning approach to reduce dimensional space in large datasets. IEEE Access8: 148181–148192.
39.
TjurT (2009) Coefficients of determination in logistic regression models—a new proposal: the coefficient of discrimination. The American Statistician63: 366–372.
40.
TokeyAIShiomaSAJamalS (2022) Analysis of spatiotemporal dynamics of e-scooter usage in Minneapolis: Effects of the built and social environment. Multimodal Transportation1: 100037.
41.
TooleJLColakSSturtB, et al. (2015) The path most traveled: travel demand estimation using big data resources. Transportation Research Part C: Emerging Technologies58: 162–177.
42.
WallerSTChandSZlojutroA, et al. (2021) Rapidex: a novel tool to estimate origin–destination trips using pervasive traffic data. Sustainability13: 11171.
43.
WangWAttanucciJPWilsonNH (2011) Bus passenger origin-destination estimation and related analyses using automated data collection systems. Journal of Public Transportation14: 131–150.
44.
WeerasekeraRSridharanMRanjitkarP (2020) Implications of spatiotemporal data aggregation on short‐term traffic prediction using machine learning algorithms. Journal of Advanced Transportation2020: 1–21.
45.
YangHZhengRLiX, et al. (2022) Nonlinear and threshold effects of the built environment on e-scooter sharing ridership. Journal of Transport Geography104: 103453.
46.
ZhangWBuehlerRBroaddusA, et al. (2021) What type of infrastructures do e-scooter riders prefer? A route choice model. Transportation Research Part D: Transport and Environment94: 102761.
47.
ZhaoPLiAPilesjöP, et al. (2022) A machine learning based approach for predicting usage efficiency of shared e-scooters using vehicle availability data. AGILE: GIScience Series3: 1–10.
48.
ZhaoJWuJFotedarS, et al. (2024) Fleet availability analysis and prediction for shared e-scooters: an energy perspective. Transportation Research Part D: Transport and Environment136: 104425.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
