EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Temporal Distribution Shift in Multi-View Financial Statement Fraud Detection: Diagnosis and a Drift-Adaptive Detector

Noah Campbell, Claire Wilson, Emma Thompson

International Journal of Information and Communication Technology Trends · 2026

DOI: 10.66525/ijictt133 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Information and Communication Technology Trends, 2026. Verfasst von Noah Campbell und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Financial statement fraud detectors are estimated on historical enforcement data and applied to filings that arrive years later, yet they are almost always evaluated as though the data-generating process were stationary. This paper treats temporal distribution shift as a first-class design constraint. Using 141,463 firm-year observations of U.S. public companies over fiscal years 1991–2014, labelled from SEC Accounting and Auditing Enforcement Releases, we decompose each filing into four heterogeneous evidence views—structural composition, accrual quality, own-history dynamics and peer-relative position—and measure covariate and prior shift separately for each view under a rolling prequential protocol with a two-year reporting gap. Three findings emerge. Encoding a filing by its within-cohort rank lowers covariate drift by a factor of eighteen relative to level- and ratio-based encodings. The discriminative power of individual views is strongly non-stationary, and no single view dominates across the twelve test years. Prior shift leaves ranking quality intact while destroying probability calibration. We then introduce TIDAL, which couples view-specific balanced-undersampling ensembles with a parameter-free drift-adaptive mixture of expanding-window and recent-window members, followed by a sampling-odds calibration stage. Across twelve rolling folds TIDAL matches the strongest published detector in mean AUC, raises worst-year AUC by 5.9 points, cuts year-to-year dispersion by 41%, and reduces expected calibration error from 0.330 to 0.002.

Zitieren

APA

Campbell, N., Wilson, C., & Thompson, E. (2026). Temporal Distribution Shift in Multi-View Financial Statement Fraud Detection: Diagnosis and a Drift-Adaptive Detector. International Journal of Information and Communication Technology Trends. https://doi.org/10.66525/ijictt133

Vancouver

Campbell N, Wilson C, Thompson E. Temporal Distribution Shift in Multi-View Financial Statement Fraud Detection: Diagnosis and a Drift-Adaptive Detector. International Journal of Information and Communication Technology Trends. 2026. doi:10.66525/ijictt133

BibTeX
@article{Campbell2026,
  author = {Campbell, Noah and Wilson, Claire and Thompson, Emma},
  title = {Temporal Distribution Shift in Multi-View Financial Statement Fraud Detection: Diagnosis and a Drift-Adaptive Detector},
  journal = {International Journal of Information and Communication Technology Trends},
  year = {2026},
  doi = {10.66525/ijictt133}
}
Kostenlos starten →