Refine
Document Type
Language
- English (2)
Publication reviewed
- begutachtet (2)
Keywords
- Carsharing (1)
- Electric vehicle (1)
- Generative adversarial network (1)
- Machine learning (1)
- Shared mobility (1)
- Synthetic data (1)
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 to real-world decision support problems in carsharing.
Sustainability is a critical challenge in modern tourism, exacerbated by climate change and globalization. Thanks to digitization, data-driven approaches constitute a key technology for addressing related issues, such as overtourism. However, the overarching complexity of the touristic data landscape, amplified by the interplay of diverse digital platform ecosystems, poses considerable challenges to both data owners and consumers. To mitigate such issues, knowledge graphs (KGs) have received significant attention. KGs focus on data quality by employing unified data models and continuous data refinements, making them well-suited for data-driven applications. Although promising, many challenges must be addressed to make KGs useful in practice. This paper overviews the state of the art of the field and identifies avenues for future research, explicitly focusing on touristic value and sustainability. Following our results, future research should focus on different areas, notably real-time knowledge graph population, distributed and parallelized processes, and ontologies for dynamic data types.