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

Authors

  • Noah Campbell University of Auckland Business School, University of Auckland, Auckland, New Zealand Author
  • Claire Wilson University of Auckland Business School, University of Auckland, Auckland, New Zealand Author
  • Emma Thompson University of Auckland Business School, University of Auckland, Auckland, New Zealand Author

DOI:

https://doi.org/10.66525/ijictt133

Keywords:

financial statement fraud, temporal distribution shift, concept drift, multi-view learning, class imbalance, probability calibration

Abstract

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.

Downloads

Download data is not yet available.

References

[1] M. D. Beneish, "The detection of earnings manipulation," Financial Analysts J., vol. 55, no. 5, pp. 24–36, 1999.

[2] P. M. Dechow, W. Ge, C. R. Larson, and R. G. Sloan, "Predicting material accounting misstatements," Contemp. Accounting Res., vol. 28, no. 1, pp. 17–82, 2011.

[3] Xing, S., Wang, Y., & Liu, W. (2025). Self-adapting CPU scheduling for mixed database workloads via hierarchical deep reinforcement learning. Symmetry, 17(7), 1109.

[4] Ji, E., Wang, Y., Xing, S., & Jin, J. (2025). Hierarchical reinforcement learning for energy-efficient API traffic optimization in large-scale advertising systems. IEEE Access.

[5] J. Perols, "Financial statement fraud detection: An analysis of statistical and machine learning algorithms," Auditing: A J. Pract. Theory, vol. 30, no. 2, pp. 19–50, 2011.

[6] M. Cecchini, H. Aytug, G. J. Koehler, and P. Pathak, "Detecting management fraud in public companies," Manage. Sci., vol. 56, no. 7, pp. 1146–1160, 2010.

[7] A. Abbasi, C. Albrecht, A. Vance, and J. Hansen, "MetaFraud: A meta-learning framework for detecting financial fraud," MIS Quart., vol. 36, no. 4, pp. 1293–1327, 2012.

[8] P. M. Dechow, R. G. Sloan, and A. P. Sweeney, "Causes and consequences of earnings manipulation: An analysis of firms subject to enforcement actions by the SEC," Contemp. Accounting Res., vol. 13, no. 1, pp. 1–36, 1996.

[9] A. Dyck, A. Morse, and L. Zingales, "How pervasive is corporate fraud?," Rev. Accounting Stud., vol. 29, no. 1, pp. 736–769, 2024.

[10] S. Walker, "Critique of an article on machine learning in the detection of accounting fraud," Econ J. Watch, vol. 18, no. 1, pp. 61–70, 2021.

[11] Wang, Y., & Xing, S. (2025). AI-driven CPU resource management in cloud operating systems. Journal of Computer and Communications, 13(06), 135-149.

[12] Xing, S., & Wang, Y. (2025). Cross-modal attention networks for multi-modal anomaly detection in system software. IEEE Open Journal of the Computer Society.

[13] E. Zavitsanos, D. Mavroeidis, K. Bougiatiotis, E. Spyropoulou, L. Loukas, and G. Paliouras, "Financial misstatement detection: A realistic evaluation," in Proc. 2nd ACM Int. Conf. AI in Finance (ICAIF), 2021, art. 34.

[14] T. Loughran and B. McDonald, "When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks," J. Finance, vol. 66, no. 1, pp. 35–65, 2011.

[15] L. Purda and D. Skillicorn, "Accounting variables, deception, and a bag of words: Assessing the tools of fraud detection," Contemp. Accounting Res., vol. 32, no. 3, pp. 1193–1223, 2015.

[16] P. Craja, A. Kim, and S. Lessmann, "Deep learning for detecting financial statement fraud," Decis. Support Syst., vol. 139, art. 113421, 2020.

[17] T. Baltrušaitis, C. Ahuja, and L.-P. Morency, "Multimodal machine learning: A survey and taxonomy," IEEE Trans. Pattern Anal. Mach. Intell., vol. 41, no. 2, pp. 423–443, 2019.

[18] J. Quiñonero-Candela, M. Sugiyama, A. Schwaighofer, and N. D. Lawrence, Eds., Dataset Shift in Machine Learning. Cambridge, MA, USA: MIT Press, 2009.

[19] J. Gama, I. Žliobaitė, A. Bifet, M. Pechenizkiy, and A. Bouchachia, "A survey on concept drift adaptation," ACM Comput. Surv., vol. 46, no. 4, art. 44, 2014.

[20] P. W. Koh et al., "WILDS: A benchmark of in-the-wild distribution shifts," in Proc. Int. Conf. Mach. Learn. (ICML), 2021, pp. 5637–5664.

[21] W. Ping, Y. Jiao, H. Fan, and X. Zhang, "Multimodal fraud detection in financial statements: A trimodal attention network with contrastive evidence chain construction," IEEE Access, vol. 14, pp. 80456–80468, 2026.

[22] H. Yao, C. Choi, B. Cao, Y. Lee, P. W. Koh, and C. Finn, "Wild-Time: A benchmark of in-the-wild distribution shift over time," in Proc. NeurIPS Datasets and Benchmarks Track, 2022.

[23] G. Bai, C. Ling, and L. Zhao, "Temporal domain generalization with drift-aware dynamic neural networks," in Proc. Int. Conf. Learn. Represent. (ICLR), 2023.

[24] A. Nasery, S. Thakur, V. Piratla, A. De, and S. Sarawagi, "Training for the future: A simple gradient interpolation loss to generalize along time," in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 34, 2021, pp. 19198–19209.

[25] Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. Lempitsky, "Domain-adversarial training of neural networks," J. Mach. Learn. Res., vol. 17, no. 59, pp. 1–35, 2016.

[26] S. Sagawa, P. W. Koh, T. B. Hashimoto, and P. Liang, "Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization," in Proc. Int. Conf. Learn. Represent. (ICLR), 2020.

[27] M. Arjovsky, L. Bottou, I. Gulrajani, and D. Lopez-Paz, "Invariant risk minimization," arXiv:1907.02893, 2019.

[28] S. Rabanser, S. Günnemann, and Z. C. Lipton, "Failing loudly: An empirical study of methods for detecting dataset shift," in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2019.

[29] J. Cao, A. Ganesh, J. Cai, R. Southwell, E. M. Perkoff, M. Regan, K. Kann, J. H. Martin, M. Palmer, and S. D'Mello, “A comparative analysis of automatic speech recognition errors in small group classroom discourse,” in Proc. 31st ACM Conf. User Modeling, Adaptation and Personalization (UMAP), 2023, pp. 250–261.

[30] Chen, T., Shang, W., & Guo, Z. (2024). Xsla: An SLA-aware heterogeneous XPU scheduling framework for edge AI inference. World Journal of Information Technology, 2(2), 48–59.

[31] Zou, J., Qin, Y., & Rhee, M. (2024). Beyond model scale: A task-aware reliability benchmark for large language models in clinical decision support. Innovation and Technology Studies, 1(1), 39–47.

[32] Fang, Q. (2024). Bias-aware large language models for equitable Fang, Q. (2024). Bias-aware large language models for equitable educational feedback and assessment. Trends in Social Sciences and Humanities Research, 2(1), 41–50.

[33] Qin, Y., Zou, J., & Rhee, M. (2022). An AI-driven intelligent transaction execution framework for internet finance platforms: Cost-sensitive real-time integrity interdiction. Eurasia Journal of Science and Technology, 4(2), 36–44.

[34] Wang, Y., & Zhang, C. (2023). AERIS: Adaptive executor scoped resource management for privacy preserving data processing in Apache Spark. Eurasia Journal of Science and Technology, 5(2), 25-33.

[35] Zhao, W., & Wang, B. (2022). CAPA: A prediction‑driven autoscaling framework for SLO‑aware cloud‑native machine learning inference. Journal of Computer Science and Electrical Engineering, 4(1), 8-16.

[36] Guo, Z., Chen, T., & Shang, W. (2022). Class‑conditional intermediate‑domain adversarial adaptation for cross‑device acoustic scene classification. Journal of Computer Science and Electrical Engineering, 4(1), 26-35

[37] Shen, A. (2023). Compute-efficient scaling of large sequential recommendation models under dynamic user behavior. World Journal of Information Technology, 1(1), 62–71.

[38] Fang, Q. (2024). True-EWS: Trustworthy early warning with equalized conformal guarantees for equitable student support in U.S. education. Educational Research and Human Development, 1(2), 44–54.

[39] Shen, A., & Huang, S. (2022). A systems-aware framework for intelligent large-scale recommendation models. Journal of Computer Science and Electrical Engineering, 4(1), 36–44.

Downloads

Published

2026-09-29