EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Auditing the Smart City: Enhancing Financial and Data Risk Management through AI Internal Audits

Muhammad Rashid Mahmood

Journal of AI Range · 17.06.2026 · 3 (2) · 13-20

DOI: 10.66320/e8s4k953 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of AI Range, online erschienen am 17.06.2026. Verfasst von Muhammad Rashid Mahmood. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid global proliferation of smart city infrastructure necessitates massive municipal capital expenditures and the deployment of ubiquitous Internet of Things (IoT) sensor networks. While these technologies drive urban efficiency, they introduce unprecedented financial risk profiles and severe data privacy vulnerabilities. Traditional internal auditing frameworks—characterized by retrospective, periodic sampling, and manual reviews—are fundamentally ill-equipped to govern the continuous, high-velocity, and high-volume data streams generated by municipal IoT ecosystems. This research empirically validates an Artificial Intelligence-driven Continuous Auditing (CA) framework to establish a proactive governance mechanism capable of real-time financial oversight and continuous data risk management within municipal deployments. The empirical approach integrates an event-driven data fusion architecture (utilizing Apache Kafka and Knowledge Graphs) to bridge asynchronous batch financial ledgers and real-time IoT logs. Advanced Machine Learning (ML) algorithms—specifically Isolation Forests for tabular anomaly detection and Long Short-Term Memory (LSTM) Deep Autoencoders for time-series analysis—are deployed to conduct simultaneous, dual-domain monitoring. Simulated empirical results demonstrate that the AI-powered Continuous Audit framework reduces risk detection latency from an average of 90 days (traditional quarterly audits) to sub-second algorithmic flagging. Evaluated using Precision-Recall Area Under Curve (PR-AUC) and F2-Scores to account for extreme anomaly imbalance, the automated approach yielded a 42.6% empirical enhancement in detecting systemic financial anomalies and a 61.3% increase in proactively mitigating data privacy breaches. This governance framework substantially advances the RC-FBSIC 2026 "Smart Cities & IoT" track by shifting the paradigm of urban risk management from retrospective compliance to continuous, proactive assurance, ensuring that sustainable urban expansion remains fiscally responsible and cryptographically secure.

Zitieren

APA

Mahmood, M. R. (2026). Auditing the Smart City: Enhancing Financial and Data Risk Management through AI Internal Audits. Journal of AI Range, 3(2), 13-20. https://doi.org/10.66320/e8s4k953

Vancouver

Mahmood MR. Auditing the Smart City: Enhancing Financial and Data Risk Management through AI Internal Audits. Journal of AI Range. 2026;3(2):13-20. doi:10.66320/e8s4k953

BibTeX
@article{Mahmood2026,
  author = {Mahmood, Muhammad Rashid},
  title = {Auditing the Smart City: Enhancing Financial and Data Risk Management through AI Internal Audits},
  journal = {Journal of AI Range},
  year = {2026},
  volume = {3},
  number = {2},
  pages = {13--20},
  doi = {10.66320/e8s4k953}
}
Kostenlos starten →