# Anomaly Detection in Double-entry Bookkeeping Data by Federated Learning System with Non-model Sharing Approach

arXiv: https://arxiv.org/abs/2501.12723 · HTML: https://mlsanity.com/paper/2501.12723/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 49 references that are in the map.
- First posted on arXiv 22 Jan 2025.

## Builds on (most cited first, 15 of 15)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Detection of Anomalies in Large Scale Accounting Data using Deep Autoencoder Networks](https://mlsanity.com/paper/1709.05254/) (2017)
- [Interpretable collaborative data analysis on distributed data](https://mlsanity.com/paper/2011.04437/) (2020)
- [Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks](https://mlsanity.com/paper/1908.00734/) (2019)
- [Accuracy and Privacy Evaluations of Collaborative Data Analysis](https://mlsanity.com/paper/2101.11144/) (2021)
- [Collaborative causal inference on distributed data](https://mlsanity.com/paper/2208.07898/) (2022)
- [Another Use of SMOTE for Interpretable Data Collaboration Analysis](https://mlsanity.com/paper/2208.12458/) (2022)
- [Federated Learning System without Model Sharing through Integration of Dimensional Reduced Data Representations](https://mlsanity.com/paper/2011.06803/) (2020)
- [Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits](https://mlsanity.com/paper/2208.12708/) (2022)
- [ADAMM: Anomaly Detection of Attributed Multi-graphs with Metadata: A Unified Neural Network Approach](https://mlsanity.com/paper/2311.07355/) (2023)
- [Data collaboration for causal inference from limited medical testing and medication data](https://mlsanity.com/paper/2501.06511/) (2025)
- [RESHAPE: Explaining Accounting Anomalies in Financial Statement Audits by enhancing SHapley Additive exPlanations](https://mlsanity.com/paper/2209.09157/) (2022)
- [Enhanced Federated Anomaly Detection Through Autoencoders Using Summary Statistics-Based Thresholding](https://mlsanity.com/paper/2410.09284/) (2024)
- [Estimation of conditional average treatment effects on distributed confidential data](https://mlsanity.com/paper/2402.02672/) (2024)

## Built on by (most cited first, 4 of 4)

- [We Need to Rethink Benchmarking in Anomaly Detection](https://mlsanity.com/paper/2507.15584/) (2025)
- [A new type of federated clustering: A non-model-sharing approach](https://mlsanity.com/paper/2506.10244/) (2025)
- [Nonlinear Data Integration via Kernel Methods for Data Collaboration Analysis](https://mlsanity.com/paper/2605.27219/) (2026)
- [Unsupervised Graph Modeling for Anomaly Detection in Accounting Subject Relationships](https://mlsanity.com/paper/2604.26216/) (2026)

## Abstract (arXiv)

Anomaly detection is crucial in financial auditing, and effective detection requires large volumes of data from multiple organizations. However, journal entry data is highly sensitive, making it infeasible to share them directly across audit firms. To address this challenge, journal entry anomaly detection methods based on model share-type federated learning (FL) have been proposed. These methods require multiple rounds of communication with external servers to exchange model parameters, which necessitates connecting devices storing confidential data to external networks -- a practice not recommended for sensitive data such as journal entries. To overcome these limitations, a novel anomaly detection framework based on data collaboration (DC) analysis, a non-model share-type FL approach, is proposed. The method first transforms raw journal entry data into secure intermediate representations via dimensionality reduction and then constructs a collaboration representation used to train an anomaly detection autoencoder. Notably, the approach does not require raw data to be exposed or devices to be connected to external networks, and the entire process needs only a single round of communication. The proposed method was evaluated on both synthetic and real-world journal entry data collected from eight healthcare organizations. The experimental results demonstrated that the framework not only outperforms the baseline trained on individual data but also achieves higher detection performance than model-sharing FL methods such as FedAvg and FedProx, particularly under non-i.i.d. settings that simulate practical audit environments. This study addresses the critical need to integrate organizational knowledge while preserving data confidentiality, contributing to the development of practical intelligent auditing systems.