• search hit 10 of 196
Back to Result List

Fake it till you make it: Synthetic data for emerging carsharing programs

  • Carsharing is an integral part of the transformation toward flexible and sustainable mobility. New carsharing programs are entering the market to challenge large operators by offering innovative services. This study investigates the use of generative machine learning models for creating synthetic data to support carsharing decision–making when data access is limited. To this end, it explores the evaluation, selection, and implementation of leading-edge methods, such as generative adversarial networks (GANs) and variational autoencoders (VAEs), to generate synthetic tabular transaction data of carsharing trips. The study analyzes usage data of an emerging carsharing program that is expanding its services to include free-floating electric vehicles (EVs). The results show that augmenting real training data with synthetic samples improves predictive modeling of upcoming trips by up to 4.63%. These results support carsharing researchers and practitioners in generating and leveraging synthetic mobility data to develop solutions toCarsharing is an integral part of the transformation toward flexible and sustainable mobility. New carsharing programs are entering the market to challenge large operators by offering innovative services. This study investigates the use of generative machine learning models for creating synthetic data to support carsharing decision–making when data access is limited. To this end, it explores the evaluation, selection, and implementation of leading-edge methods, such as generative adversarial networks (GANs) and variational autoencoders (VAEs), to generate synthetic tabular transaction data of carsharing trips. The study analyzes usage data of an emerging carsharing program that is expanding its services to include free-floating electric vehicles (EVs). The results show that augmenting real training data with synthetic samples improves predictive modeling of upcoming trips by up to 4.63%. These results support carsharing researchers and practitioners in generating and leveraging synthetic mobility data to develop solutions to real-world decision support problems in carsharing.show moreshow less

Download full text files

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Tobias Albrecht, Robert KellerORCiDGND, Dominik RebholzORCiD, Maximilian Röglinger
DOI:https://doi.org/10.1016/j.trd.2024.104067
Identifier:1361-9209 OPAC HS OPAC extern
Identifier:1879-2340 OPAC HS OPAC extern
Parent Title (English):Transportation Research Part D
Publisher:Elsevier
Place of publication:Amsterdam
Document Type:Article
Language:English
Date of Publication (online):2024/01/17
Year of first Publication:2024
Tag:Carsharing; Electric vehicle; Generative adversarial network; Machine learning; Shared mobility; Synthetic data
Volume:28
Issue:127 / Februar
Article Number:104067
Number of pages:20 Seiten
First Page:1
Last Page:20
Institutes:Fakultät Tourismus-Management
INIT – Institut für Nachhaltige und Innovative Tourismusentwicklung
Open Access:open_access
Research focus:FSP1: Energie
FSP2: Mobilität
FSP4: Soziale Innovationen
Publication Lists:Keller, Robert
Rebholz, Dominik
Publication reviewed:begutachtet
Licence (German):Creative Commons - CC BY - Namensnennung 4.0 International
Release Date:2024/02/01
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.