Explaining Anomalies using Denoising Autoencoders for Financial Tabular Data

@article{Sattarov2022ExplainingAU,
  title={Explaining Anomalies using Denoising Autoencoders for Financial Tabular Data},
  author={Timur Sattarov and Dayananda Herurkar and J{\"o}rn Hees},
  journal={ArXiv},
  year={2022},
  volume={abs/2209.10658}
}
Recent advances in Explainable AI (XAI) increased the demand for deployment of safe and interpretable AI models in various industry sectors. Despite the latest success of deep neural networks in a variety of domains, understanding the decision-making process of such complex models still remains a challenging task for domain experts. Especially in the financial domain, merely pointing to an anomaly composed of often hundreds of mixed type columns, has limited value for experts. Hence, in this… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 47 REFERENCES

Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks

It is demonstrated that such artificial neural networks are capable of learning a semantic meaningful representation of real-world journal entries that provides a holistic view on a given set of journal entries and significantly improves the interpretability of detected accounting anomalies.

Detection of Anomalies in Large Scale Accounting Data using Deep Autoencoder Networks

This work proposes the application of deep autoencoder neural networks to detect anomalous journal entries and demonstrates that the trained network's reconstruction error obtainable for a journal entry and regularized by the entry's individual attribute probabilities can be interpreted as a highly adaptive anomaly assessment.

Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models

Explaining Anomalies Detected by Autoencoders Using SHAP

A game theory-based framework known as SHapley Additive exPlanations is extended to explain anomalies detected by an autoencoder, an unsupervised model, aiming at minimizing the false positive rate of detected anomalies.

GEE: A Gradient-based Explainable Variational Autoencoder for Network Anomaly Detection

GEE comprises of two components:Variational Autoencoder (VAE)- an unsupervised deep-learning technique for detecting anomalies, and a gradient-based fingerprinting technique for explaining anomalies.

Why do tree-based models still outperform deep learning on tabular data?

Results show that tree-based models remain state-of-the-art on medium-sized data even without accounting for their superior speed, and leads to a series of challenges which should guide researchers aiming to build tabular-species NNs.

Deep Neural Networks and Tabular Data: A Survey

An in-depth overview of state-of-the-art deep learning methods for tabular data, categorizing these methods into three groups: data transformations, specialized architectures, and regularization models, and indicates that algorithms based on gradient-boosted tree ensembles still mostly outperform deep learning models on supervised learning tasks, suggesting that the research progress on competitive deep learning model development is stagnating.

Learning to Validate the Predictions of Black Box Machine Learning Models on Unseen Data

This work proposes an approach to assist non-ML experts working with pretrained ML models with a performance predictor for pretrained black box models, which can be combined with the model, and automatically warns end users in case of unexpected performance drops.

Scalable and Interpretable One-class SVMs with Deep Learning and Random Fourier features

This paper proposes autoencoder based one-class support vector machine (AE-1SVM) that brings OC-SVM into deep learning context by combining it with a representation learning architecture and jointly exploit stochastic gradient descent to obtain end-to-end training.

Deep Learning Anomaly Detection as Support Fraud Investigation in Brazilian Exports and Anti-Money Laundering

The results obtained are presented in implementing the unsupervised Deep Learning model to classify Brazilian exporters regarding the possibility of committing fraud in exports, and the model was able to detect anomalies in at least twenty exporters.