How do tax authorities detect falsified documents and hidden assets?

Numbers match the citations in the article. A working link isn't proof that a page supports a claim; check the quoted passage and date.

1. 1

   FORENSIC ACCOUNTING METHODS AND VALUE-ADDED TAX FRAUD

   Journal of Southwest Jiaotong University (Alshira’h & Lutfi)Published Jan 1, 2023Checked Oct 12, 2026

   “Using PLS-SEM analysis, it was found that three factors could be extracted from forensic accounting methods; namely, investigation operations, procedures, and evaluation processes have a significant effect on value-added tax fraud. This empirical investigation was conducted only in Jordan. Because it is very likely to obtain different results in other nations, the findings cannot be applied to other business environments. Fraud behavior can be explored by investigation operations, procedures, and evaluation processes as an application of forensic accounting methods. Findings of this paper may highlight the amazing relationship between forensic accounting methods and value-added tax fraud for policymakers, regulators, and other stakeholders in developing nations, notably in Jordan. This could pave the way for effective forensic accounting methods for fraud. By demonstrating empirical findings, this study fills the gap in the existing literature and knowledge. Keywords: Forensic Accounting, Investigation Operations, Procedures, Evaluation Processes, Value-Added Tax Fraud DOI： https://doi.org/10.35741/issn.0258-2724.58.3.78”

2. 2

   Forensic Accounting, Tax Fraud and Tax Evasion in Nigeria – Review of Literatures and Matter for Policy Consideration

   International Journal of Emerging Trends in Social Sciences (Augustine et al.)Published Jan 1, 2020Checked Oct 12, 2026

   “This called for a shift to tax revenues (TR) but the major challenge is the high rate of TF and TE. One way of reducing this menace and to instil Tax Compliance (TC) is the application of Forensic Accounting (FA) techniques. Therefore, this call for better understanding of the concepts and ways of using FA to promote TC. It is against this background that the study examined FA, TF and TE in Nigeria. The study adopts exploratory research design with literatures from materials on taxation and accounting. The study concluded that since the traditional auditing techniques has failed to curb TF and TE because of its inefficiency and ineffectiveness of operation, therefore FA will expose, control and deter fraudulent practices on TR, and this will enhance good TR for the government. The study recommends that government should develop interest in FA, enforce tax laws and regulations on TF and TE with strict appropriate punishment on tax evaders, ensure transparency and accountability on TR, and further create forensic unit in tax offices with modern FA techniques equipment.”

3. 3

   Audit lead selection and yield prediction from historical tax data using artificial neural networks.

   PloS one (Chan et al.)Published Nov 30, 2022Checked Oct 12, 2026

   “Tax audits are a crucial process adopted in all tax departments to ensure tax compliance and fairness. Traditionally, tax audit leads have been selected based on empirical rules and randomization methods, which are not adaptive, may miss major cases and can introduce bias. Here, we present an audit lead tool based on artificial neural networks that have been trained and evaluated on an integrated dataset of 93,413 unique tax records from 8,647 restaurant businesses over 10 years in the Northern California, provided by the California Department of Tax and Fee Administration (CDTFA). The tool achieved a 40.1% precision and 58.7% recall (F1-score of 0.42) on classifying positive audit leads, and the corresponding regressor provided estimated audit gains (MAE of $155,490). Finally, we evaluated the statistical significance of various empirical rules for use in lead selection, with two out of five being supported by the data. This work demonstrates how data can be leveraged for creating evidence-based models of audit selection and validating empirical hypotheses, resulting in higher audit yields and more fair audit selection processes.”

4. 4

   Minimizing unnecessary tax audits using multi-objective hyperparameter tuning of XGBoost with focal loss.

   Frontiers in artificial intelligence (Malashin et al.)Published Oct 16, 2025Checked Oct 12, 2026

   “Given its computational efficiency, XGBoost was selected as the primary model. However, class imbalance persisted even among young companies, necessitating the integration of focal loss to improve classification performance. To further enhance accuracy while maintaining model interpretability, NSGA-II (Non-dominated Sorting Genetic Algorithm II) was used for multi-objective hyperparameter optimization of XGBoost. The objectives were to maximize ROC-AUC for improved predictive performance and minimize the number of trees to enhance interpretability. The optimized model achieved a ROC-AUC of 0.9417, compared to 0.9161 without optimization, demonstrating the effectiveness of this approach. Additionally, SHAP analysis provided insights into key factors influencing non-compliance, supporting explainability and aiding regulatory decision-making. This methodology contributes to fair and efficient oversight by reducing unnecessary inspections, minimizing disruptions to compliant businesses, and improving the overall effectiveness of tax compliance monitoring.”

5. 5

   Documents falsified to evade tax on Abramovich's wealth, BBC finds

   BBC NewsPublished Oct 12, 2026Checked Oct 12, 2026

   “Backdated paperwork also made the Russian oligarch’s yachts and mansions disappear from accounts, investigation finds.”

6. 6

   TEDM-PU: A Tax Evasion Detection Method Based on Positive and Unlabeled Learning

   IEEE International Conference on Big Data (BigData) (Wu et al.)Published Dec 1, 2019Checked Oct 12, 2026

   “To train an effective model to detect tax evaders, a large amount of data is required, especially sufficient labeled data. However, the expensive and time-consuming annotation process results in small amount of labeled data being available, which makes the development of detection models difficult. To address this issue, we propose a tax evasion detection method based on positive and unlabeled learning (TEDM-PU), to identify tax evasion by utilizing limited annotated tax evasion taxpayers and a large amount of unlabeled data. The TEDM-PU framework consists of three stages: a preprocessing stage extracting taxpayer features based on random forest, a pseudo labeling stage assigning pseudo labels to unlabeled samples based on PUAdapter, and a model training stage based on LightGBM method. To evaluate the effectiveness of our proposed TEDM-PU, we conduct experimental tests on real-world tax data. The results demonstrate that TEDM-PU method can detect tax evaders with higher accuracy and better interpretability than state-of-the-art methods.”

7. 7

   IRTED-TL: An Inter-Region Tax Evasion Detection Method Based on Transfer Learning

   Research paper (Zhu et al.)Published Aug 1, 2018Checked Oct 12, 2026

   “When sufficient tax data are not readily available, the development of a representative detection model is more difficult due to unequal feature distributions in different regions. Existing methods face a challenge in explaining and tracing derived results. To overcome these challenges, we propose an Inter-Region Tax Evasion Detection method based on Transfer Learning (IRTED-TL), which is optimized to simultaneously augment training data and induce interpretability into the detection model. We exploit evasion-related knowledge in one region and leverage transfer learning techniques to reinforce the tax evasion detection tasks of other regions in which training examples are lacking. We provide a unified framework that takes advantage of auxiliary data using a transfer learning mechanism and builds an interpretable classifier for inter-region tax evasion detection. Experimental tests based on real-world tax data demonstrate that the IRTED-TL can detect tax evaders with higher accuracy and better interpretability than existing methods.”

8. 8

   INTEGRATING FORENSIC ACCOUNTING AND TECHNOLOGY: A LIFECYCLE FRAMEWORK FOR TAX FRAUD COUNTERACTION

   Social Development Economic and Legal Issues (Asare)Published Sep 14, 2025Checked Oct 12, 2026

   “Established around three interconnected stages of prevention, detection, and correction, the model combines forensic expertise with intelligent technologies to enhance transparency, strengthen enforcement capacity, and support institutional accountability. It is based on five theoretical perspectives: the Fraud Triangle, Institutional Theory, Control Theory, the Technology Acceptance Model, and the Theory of National Economic Security. With relevance for developing economies where enforcement capacity is limited, the framework highlights the need for specialist teams, digital risk assessment, secure audit systems, and stronger inter-agency collaboration. As a conceptual model, the FTTTF still requires empirical validation, but it offers a basis for future research and policy experimentation. By reframing digital tax enforcement as a strategic component of economic governance rather than a purely technical function, the study offers a scalable tool for improving compliance and strengthening government accountability.”