# Tax Evasion Risk Management Using a Hybrid Unsupervised Outlier Detection Method

arXiv: https://arxiv.org/abs/2103.01033 · HTML: https://mlsanity.com/paper/2103.01033/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 51 references that are in the map.
- First posted on arXiv 25 Feb 2021.

## Builds on (most cited first, 6 of 6)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyOD: A Python Toolbox for Scalable Outlier Detection](https://mlsanity.com/paper/1901.01588/) (2019)
- [Deep Learning for Anomaly Detection: A Review](https://mlsanity.com/paper/2007.02500/) (2020)
- [How to Evaluate the Quality of Unsupervised Anomaly Detection Algorithms?](https://mlsanity.com/paper/1607.01152/) (2016)
- [Detection of Anomalies in Large Scale Accounting Data using Deep Autoencoder Networks](https://mlsanity.com/paper/1709.05254/) (2017)
- [An Evolutionary Game Model for Understanding Fraud in Consumption Taxes](https://mlsanity.com/paper/2101.04424/) (2021)

## Built on by (most cited first, 3 of 3)

- [TED: Related Party Transaction guided Tax Evasion Detection on Heterogeneous Graph](https://mlsanity.com/paper/2605.26984/) (2026)
- [Attention, Anomalies! Handling Attention Layers in Unsupervised Federated Outlier Detection](https://mlsanity.com/paper/2608.04753/) (2026)
- [Federated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly Detection](https://mlsanity.com/paper/2608.08906/) (2026)

## Abstract (arXiv)

Big data methods are becoming an important tool for tax fraud detection around the world. Unsupervised learning approach is the dominant framework due to the lack of label and ground truth in corresponding data sets although these methods suffer from low interpretability. HUNOD, a novel hybrid unsupervised outlier detection method for tax evasion risk management, is presented in this paper. In contrast to previous methods proposed in the literature, the HUNOD method combines two outlier detection approaches based on two different machine learning designs (i.e, clustering and representational learning) to detect and internally validate outliers in a given tax dataset. The HUNOD method allows its users to incorporate relevant domain knowledge into both constituent outlier detection approaches in order to detect outliers relevant for a given economic context. The interpretability of obtained outliers is achieved by training explainable-by-design surrogate models over results of unsupervised outlier detection methods. The experimental evaluation of the HUNOD method is conducted on two datasets derived from the database on individual personal income tax declarations collected by the Tax Administration of Serbia. The obtained results show that the method indicates between 90% and 98% internally validated outliers depending on the clustering configuration and employed regularization mechanisms for representational learning.