About Me

Since mid-2024, I have been with the Swiss Federal Audit Office (SFAO), where I contribute on the intersection of agentic artificial intelligence and financial auditing. My work aims to develop novel approaches leveraging deep learning techniques to make our audits more effective.

Previously, I was a DAAD IFI Postdoc at the International Computer Science Institute (ICSI), affiliated with UC Berkeley. Before, I completed a Ph.D. at the University of St.Gallen (HSG) within the AI:ML research group, under the supervision of Damian Borth and Miklos A. Vasarhelyi. During my Ph.D., I was a visiting Swiss Mobi.Doc research fellow at the Continuous Audit and Reporting Research Lab (CARLab) at Rutgers University from 2022 to 2023.

After graduating from the University of Mannheim, I spent nearly a decade working in the Forensic Services practice at PricewaterhouseCoopers (PwC), specializing in advanced data analytics for forensic accounting and fraud investigations.

       

Recent News

Selected Publications

Please see my Google Scholar for a complete list.

Journal Publications

Artificial Intelligence Co-Piloted Auditing
H. Gu, M. Schreyer, K. Moffitt, and Miklos A. Vasarhelyi
International Journal of Accounting Information Systems 54, 2024

[html], [pdf]

Conference Publications

Imb-FinDiff: Conditional Diffusion Models for Class Imbalance Synthesis of Financial Tabular Data
M. Schreyer, T. Sattarov, A. Sim, and K. Wu
ACM International Conference on Artificial Intelligence in Finance (ICAIF), 2024
[html], [pdf]

FinDiff: Diffusion Models for Financial Tabular Data Generation
T. Sattarov, M. Schreyer, and D. Borth
ACM International Conference on Artificial Intelligence in Finance (ICAIF), 2023

[html], [pdf]

Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits
M. Schreyer, T. Sattarov, and D. Borth
ACM International Conference on Artificial Intelligence in Finance (ICAIF), 2022
[html], [pdf]

RESHAPE: Explaining Accounting Anomalies in Financial Statement Audits by enhancing SHapley Additive exPlanations
R. Mueller, M. Schreyer, T. Sattarov, and D. Borth
ACM International Conference on Artificial Intelligence in Finance (ICAIF), 2022
[html], [pdf]

Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations for Downstream Audit Tasks
M. Schreyer, T. Sattarov, and D. Borth
ACM International Conference on Artificial Intelligence in Finance (ICAIF), 2021
[html], [pdf]

Learning Sampling in Financial Statement Audits using Vector Quantised Variational Autoencoder Neural Networks
M. Schreyer, T. Sattarov, A. Gierbl, B. Reimer, and D. Borth
ACM International Conference on Artificial Intelligence in Finance (ICAIF), 2020
[html], [pdf]

Detection of Anomalies in Large-Scale Accounting Data using Deep Autoencoder Networks
M. Schreyer, T. Sattarov, D. Borth, A. Dengel, and B. Reimer
Nvidia’s GPU Technology Conference (GTC), 2018
[html], [pdf]

Workshop Publications

FedTabDiff: Federated Learning of Diffusion Probabilistic Models for Synthetic Mixed-Type Tabular Data Generation
T. Sattarov, M. Schreyer, and D. Borth
AAAI Workshop on AI in Finance for Social Impact (AIFinSi), 2024
[html], [pdf], [poster]

Federated Continual Learning to Detect Accounting Anomalies in Financial Auditing
M. Schreyer, H. Hemati, D. Borth, and Miklos A. Vasarhelyi
NeurIPS Workshop on Federated Learning (NeurIPS-FL), 2022
[html], [pdf], [poster]

Continual Learning for Unsupervised Anomaly Detection in Continuous Auditing of Financial Accounting Data
H. Hemati, M. Schreyer, and D. Borth
AAAI Workshop on AI in Financial Services (AAAI-WFS), 2022
[html], [pdf]

Leaking Sensitive Financial Accounting Data in Plain Sight using Deep Autoencoder Neural Networks
M. Schreyer, C. Schulze, and D. Borth
AAAI Workshop on KD in Financial Services (AAAI-KDF), 2021
[html], [pdf]

Adversarial Learning of Deepfakes in Accounting
M. Schreyer, T. Sattarov, B. Reimer, and D. Borth
NeurIPS Workshop on Robust AI in Financial Services (NeurIPS), 2019

[html], [pdf]

Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks
M. Schreyer, T. Sattarov, C. Schulze, B. Reimer, and D. Borth
KDD Workshop on Anomaly Detection in Finance (KDD), 2019
[html], [pdf]

ArXiv and SSRN Preprints

Artificial Intelligence Agentic Auditing
H. Gu, M. Schreyer, K. Moffitt, and Miklos A. Vasarhelyi
Preprint available open-access (SSRN), 2024

[html], [pdf]

Differentially Private Federated Learning of Diffusion Models for Synthetic Tabular Data Generation
T. Sattarov, M. Schreyer, and D. Borth
Preprint available open-access (arXiv), 2024
[html], [pdf]

Deep Learning Meets Risk-Based Auditing: A Holistic Framework for Leveraging Foundation and Task-Specific Models in Audit Procedures
T. Föhr, M. Schreyer, K. Moffitt, and K.-U. Marten
Preprint available open-access (SSRN), 2024
[html], [pdf]

Accounting & Auditing Practitioner Journal Publications

A Graph Says More Than A Thousand Journal Entries - Harnessing Graph Autoencoder Networks in Auditing
Q. Huang, M. Schreyer, N.R. Michiles, and M.A. Vasarhelyi
EXPERTsuisse, Expert Focus (12), 653-659 (Expert Focus), 2024
[tba], [tba]

Collective Artificial Intelligence in Auditing - Advancing Audit Models through Federated Learning Without Sharing Proprietary Data
M. Schreyer, D. Borth, T.F. Ruud, and M.A. Vasarhelyi
EXPERTsuisse, Expert Focus (04), 180-186 (Expert Focus), 2024
[html], [pdf]

Artificial Intelligence Enabled Audit Sampling - Learning to Draw Representative Audit Samples from Large-Scale Journal Entry Data
M. Schreyer, A.S. Gierbl, T.F. Ruud, and D. Borth
EXPERTsuisse, Expert Focus (04), 106-112 (Expert Focus), 2022
[html], [pdf]

Artificial Intelligence in Internal Audit as a Contribution to Effective Governance - Deep-learning Enabled Detection of Anomalies
M. Schreyer, M. Baumgartner, T.F. Ruud, and D. Borth
EXPERTsuisse, Expert Focus (01), 45-50 (Expert Focus), 2022
[html], [pdf]

Accounting & Auditing Practitioner Journal Publications (in German)

Generative Künstliche Intelligenz und Risikoorientierter Prüfungsansatz
T. L. Föhr, K.-U. Marten, and M. Schreyer
Der Betrieb, Nr. 30, 1681-1693, 2023

[non open access]

Stichprobenauswahl durch die Anwendung von Künstlicher Intelligenz - Lernen repräsentativer Stichproben aus Journalbuchungen
M. Schreyer, A.S. Gierbl, T.F. Ruud, and D. Borth
EXPERTsuisse, Expert Focus (02), 10-18 (Expert Focus), 2022
[html], [pdf]

Künstliche Intelligenz im Internal Audit als Beitrag zur Effektiven Governance - Deep-Learning basierte Detektion von Buchungsanomalien
M. Schreyer, M. Baumgartner, T.F. Ruud, and D. Borth
EXPERTsuisse, Expert Focus (01), 39-44 (Expert Focus), 2022
[html], [pdf]

Deep Learning für die Wirtschaftsprüfung - Eine Darstellung von Theorie, Funktionsweise und Anwendungsmöglichkeiten
A.S. Gierbl, M. Schreyer, P. Leibfried, and D. Borth
Zeitschrift für Internationale Rechnungslegung (07/08), 349-355 (IRZ), 2021
[non open access]

Künstliche Intelligenz in der Prüfungspraxis - Eine Bestandsaufnahme aktueller Einsatzmöglichkeiten und Herausforderungen
A.S. Gierbl, M. Schreyer, P. Leibfried, and D. Borth
EXPERTsuisse, Expert Focus (09), 612-617 (Expert Focus), 2020
[html], [pdf]

Künstliche Intelligenz in der Wirtschaftsprüfung - Identifikation ungewöhnlicher Buchungen in der Finanzbuchhaltung
M. Schreyer, T. Sattarov, D. Borth, A. Dengel, and B. Reimer
WPg - Die Wirtschaftsprüfung 72 (11), 674-681 (WPg), 2018
[non open access]

Invited Teaching & Guest Lectures

Conference Presentations & Invited Talks

  • 11/2022: Adversarial Learning of Deepfakes in Accounting, The 53rd World Continuous Auditing & Reporting Symposium (WCARS), Rutgers University, view [Slides].

  • 11/2022: Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits, 3rd ACM International Conference on AI in Finance (ICAIF), view [Slides].

  • 08/2022: Deep Learning in Financial Auditing, Summer 2022 Weekly Technology Forum, Rutgers University, view [Slides] and [Video 1], [Video 2], [Video 3], [Video 4], [Video 5].

  • 11/2021: Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations, 2nd ACM International Conference on AI in Finance (ICAIF), view [Slides].

  • 04/2021: Learning Sampling in Financial Statement Audits using Vector Quantised Autoencoder Networks, Nvidia’s GPU Technology Conference (GTC), view [Slides] and [Video].

  • 03/2021: Towards Financial Fraud Detection using Deep Learning, Hong Kong Machine Learning Meetup (HKML), view [Slides] and [Video].

  • 02/2021: Leaking Accounting Data in Plain Sight using Deep Autoencoder Networks, AAAI Workshop on Knowledge Discovery from Unstructured Data in Finance, view [Slides].

  • 10/2020: Learning Sampling in Financial Auditing using Vector Quantised Autoencoder Networks, 1st ACM International Conference on AI in Finance (ICAIF), view [Slides].

  • 08/2019: Detection of Accounting Anomalies using Adversarial Autoencoder Neural Networks, 2nd KDD Workshop on Anomaly Detection in Finance, view [Slides].

  • 04/2019: Creation of Adversarial Accounting Records to Attack Financial Statement Audits, Nvidia’s GPU Technology Conference (GTC), view [Slides] and [Video].

Last updated: December 29, 2024 (using OpenAI’s GPT-4)