EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Business Value of Privacy-Preserving Mobility Analytics in Platform Operations: A Federated Risk-Utility Framework

Jiahui Ding, Fafa (Monica) Yan

Journal of Business and Data Analytics · 30.09.2026 · 4 (9) · 129-148

DOI: 10.63646/bpul9289 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Business and Data Analytics, online erschienen am 30.09.2026. Verfasst von Jiahui Ding und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mobility platforms use location and movement information to forecast demand, allocate capacity, and improve service, but the same information can expose sensitive patterns about individuals. Federated analytics can reduce the need to pool raw data, although model updates, participation records, and released outputs may still leak information. This article develops a risk–utility framework for evaluating the business value of privacy-preserving mobility analytics in platform operations. The framework links a defined operational decision to expected service gains, deployment costs, residual incident losses, and separately enforced privacy, security, and service constraints. It distinguishes centralized data pooling, federated learning, and a federated design with secure aggregation and a properly specified differential privacy mechanism. A hypothetical monthly decision example compares the alternatives using stated assumptions: their respective expected incremental values are 104, 112, and 106 thousand US dollars, making ordinary federation the highest-valued option in the baseline scenario. The ranking changes when the severity of modeled incidents increases, and privacy requirements may independently exclude an option. A separate one-release Gaussian mechanism illustrates how a formal user-level privacy statement depends on the unit of protection, clipping, the fixed denominator, and the trust boundary; it does not establish a privacy guarantee for multi-round federated training. The calculations are analytical illustrations rather than results from an implemented system or observed platform data. The article concludes with an evaluation protocol addressing causal business impact, heterogeneous participants, fairness, privacy accounting, and deployment governance.

Zitieren

APA

Ding, J., & Yan, F. M. (2026). Business Value of Privacy-Preserving Mobility Analytics in Platform Operations: A Federated Risk-Utility Framework. Journal of Business and Data Analytics, 4(9), 129-148. https://doi.org/10.63646/bpul9289

Vancouver

Ding J, Yan FM. Business Value of Privacy-Preserving Mobility Analytics in Platform Operations: A Federated Risk-Utility Framework. Journal of Business and Data Analytics. 2026;4(9):129-148. doi:10.63646/bpul9289

BibTeX
@article{Ding2026,
  author = {Ding, Jiahui and Yan, Fafa (Monica)},
  title = {Business Value of Privacy-Preserving Mobility Analytics in Platform Operations: A Federated Risk-Utility Framework},
  journal = {Journal of Business and Data Analytics},
  year = {2026},
  volume = {4},
  number = {9},
  pages = {129--148},
  doi = {10.63646/bpul9289}
}
Kostenlos starten →