A mechanism-guided simulation framework for synthetic tax-risk data: Constraint validation and reproducible benchmarking
- 1Business School, University of Shanghai for Science and Technology, Shanghai, China
Abstract
Synthetic benchmarks can support tax-risk method development when administrative records are inaccessible, but a simulator can also predetermine the patterns later reported as detection findings. We present the Tax Data Generation Model (TDGM), a mechanism-guided simulator that enforces specified income-statement and balance-sheet identities, generates a three-year panel for 10,000 firms, and injects four prespecified risk strategies. This study uses no administrative audit data; its purpose is to test whether the implementation reproduces its design assumptions and to provide a reproducible benchmark. All predictive evaluations used five repeated 70/30 group splits by firm, so no firm appeared in both training and test data. Observed marginal effects were heterogeneous rather than uniformly small: for all risky observations, Cohen’s d was −1.29 for profit margin, −1.20 for tax burden, 1.05 for the transfer-pricing indicator, and 0.15 for the income-gap ratio. In a controlled cross-sectional comparison, raw CTGAN failed both row-level accounting identities, whereas deterministic projection restored 100% validity but worsened dependence fidelity. Under the revised classifier specification, a one-hidden-layer neural network with conventional L2 regularization achieved mean ROC-AUC 0.9942 and PR-AUC 0.9710; XGBoost achieved 0.9714 and 0.8975, respectively. Removing the income-gap ratio changed XGBoost ROC-AUC only from 0.9714 to 0.9702, while restricting the model to raw Level 1 variables reduced it to 0.8941. At 1% prevalence, XGBoost ROC-AUC remained 0.9720 but PR-AUC fell to 0.6703, showing why prevalence-sensitive metrics are required. Together, the three contributions are a constraint-by-construction simulator, a reusable audit protocol for mechanism-guided generators, and explicit measurement of the accounting-repair/statistical-fidelity trade-off. Because selected flows are changed after stock generation, derived ratios can carry design-induced information. These are internal properties of a synthetic data-generating process, not estimates of real tax-evasion behavior or deployable audit performance.
Related
- JUMP-lite: Compact, reproducible benchmarking of cell representations
- GalaxyMemMD: an end-to-end Galaxy toolset for reproducible membrane embedding, molecular dynamics simulation, and analysis of membrane proteins
- BCell-Epitope-Prediction: A local, reproducible pipeline for multi-epitope vaccine design: integration and structural validation against a panel of PDB antigen-antibody complexes
- PyFLI: A Python Library for Simulation, Parameter Estimation, and Benchmarking in Fluorescence Lifetime Imaging
- Benchmarking circRNA Detection Tools from Long-Read Sequencing Using Data-Driven and Flexible Simulation Framework
BibTeX
@article{fan2026mechanismguided,
title = {{A mechanism-guided simulation framework for synthetic tax-risk data: Constraint validation and reproducible benchmarking}},
author = {Xiaojing Fan},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0353137},
url = {https://doi.org/10.1371/journal.pone.0353137},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A mechanism-guided simulation framework for synthetic tax-risk data: Constraint validation and reproducible benchmarking
AU - Xiaojing Fan
PY - 2026
DA - 2026/10/01
JO - PLOS One
DO - 10.1371/journal.pone.0353137
UR - https://doi.org/10.1371/journal.pone.0353137
AB - Synthetic benchmarks can support tax-risk method development when administrative records are inaccessible, but a simulator can also predetermine the patterns later reported as detection findings. We present the Tax Data Generation Model (TDGM), a mechanism-guided simulator that enforces specified income-statement and balance-sheet identities, generates a three-year panel for 10,000 firms, and injects four prespecified risk strategies. This study uses no administrative audit data; its purpose is to test whether the implementation reproduces its design assumptions and to provide a reproducible benchmark. All predictive evaluations used five repeated 70/30 group splits by firm, so no firm appeared in both training and test data. Observed marginal effects were heterogeneous rather than uniformly small: for all risky observations, Cohen’s d was −1.29 for profit margin, −1.20 for tax burden, 1.05 for the transfer-pricing indicator, and 0.15 for the income-gap ratio. In a controlled cross-sectional comparison, raw CTGAN failed both row-level accounting identities, whereas deterministic projection restored 100% validity but worsened dependence fidelity. Under the revised classifier specification, a one-hidden-layer neural network with conventional L2 regularization achieved mean ROC-AUC 0.9942 and PR-AUC 0.9710; XGBoost achieved 0.9714 and 0.8975, respectively. Removing the income-gap ratio changed XGBoost ROC-AUC only from 0.9714 to 0.9702, while restricting the model to raw Level 1 variables reduced it to 0.8941. At 1% prevalence, XGBoost ROC-AUC remained 0.9720 but PR-AUC fell to 0.6703, showing why prevalence-sensitive metrics are required. Together, the three contributions are a constraint-by-construction simulator, a reusable audit protocol for mechanism-guided generators, and explicit measurement of the accounting-repair/statistical-fidelity trade-off. Because selected flows are changed after stock generation, derived ratios can carry design-induced information. These are internal properties of a synthetic data-generating process, not estimates of real tax-evasion behavior or deployable audit performance.
SN - 1932-6203
ER -