# RESHAPE: Explaining Accounting Anomalies in Financial Statement Audits by enhancing SHapley Additive exPlanations

arXiv: https://arxiv.org/abs/2209.09157 · HTML: https://mlsanity.com/paper/2209.09157/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 54 references that are in the map.
- First posted on arXiv 19 Sep 2022.

## Builds on (most cited first, 22 of 22)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [On quantitative aspects of model interpretability](https://mlsanity.com/paper/2007.07584/) (2020)
- [Synthetic Benchmarks for Scientific Research in Explainable Machine Learning](https://mlsanity.com/paper/2106.12543/) (2021)
- [Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning models](https://mlsanity.com/paper/2001.11757/) (2020)
- [A Survey on the Robustness of Feature Importance and Counterfactual Explanations](https://mlsanity.com/paper/2111.00358/) (2021)
- [Explaining Anomalies Detected by Autoencoders Using SHAP](https://mlsanity.com/paper/1903.02407/) (2019)
- [To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods](https://mlsanity.com/paper/2106.00461/) (2021)
- [Contextual Outlier Interpretation](https://mlsanity.com/paper/1711.10589/) (2017)
- [Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detection](https://mlsanity.com/paper/1909.03495/) (2019)
- [Detection of Anomalies in Large Scale Accounting Data using Deep Autoencoder Networks](https://mlsanity.com/paper/1709.05254/) (2017)
- [Utilizing XAI technique to improve autoencoder based model for computer network anomaly detection with shapley additive explanation(SHAP)](https://mlsanity.com/paper/2112.08442/) (2021)
- [Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks](https://mlsanity.com/paper/1908.00734/) (2019)
- [Instance-Level Explanations for Fraud Detection: A Case Study](https://mlsanity.com/paper/1806.07129/) (2018)
- [Explainable Machine Learning for Fraud Detection](https://mlsanity.com/paper/2105.06314/) (2021)
- [Developing a Fidelity Evaluation Approach for Interpretable Machine Learning](https://mlsanity.com/paper/2106.08492/) (2021)
- [Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations for Downstream Audit Tasks](https://mlsanity.com/paper/2109.11201/) (2021)

## Built on by (most cited first, 2 of 2)

- [A Comprehensive Review on Financial Explainable AI](https://mlsanity.com/paper/2309.11960/) (2023)
- [Anomaly Detection in Double-entry Bookkeeping Data by Federated Learning System with Non-model Sharing Approach](https://mlsanity.com/paper/2501.12723/) (2025)

## Abstract (arXiv)

Detecting accounting anomalies is a recurrent challenge in financial statement audits. Recently, novel methods derived from Deep-Learning (DL) have been proposed to audit the large volumes of a statement's underlying accounting records. However, due to their vast number of parameters, such models exhibit the drawback of being inherently opaque. At the same time, the concealing of a model's inner workings often hinders its real-world application. This observation holds particularly true in financial audits since auditors must reasonably explain and justify their audit decisions. Nowadays, various Explainable AI (XAI) techniques have been proposed to address this challenge, e.g., SHapley Additive exPlanations (SHAP). However, in unsupervised DL as often applied in financial audits, these methods explain the model output at the level of encoded variables. As a result, the explanations of Autoencoder Neural Networks (AENNs) are often hard to comprehend by human auditors. To mitigate this drawback, we propose (RESHAPE), which explains the model output on an aggregated attribute-level. In addition, we introduce an evaluation framework to compare the versatility of XAI methods in auditing. Our experimental results show empirical evidence that RESHAPE results in versatile explanations compared to state-of-the-art baselines. We envision such attribute-level explanations as a necessary next step in the adoption of unsupervised DL techniques in financial auditing.