{
  "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.",
  "abstract_shown": true,
  "affiliations": [
    "Business School, University of Shanghai for Science and Technology, Shanghai, China"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Xiaojing Fan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a9ep0cnzxth9r.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0353137",
  "fulltext_url": null,
  "id": "a9ep0cnzxth9r",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0353137",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2002|Taxation and Compliance Studies"
    ],
    [
      "plos",
      "/Biology and life sciences/Cell biology/Signal transduction/Cell signaling/Signaling cascades/Stress signaling cascade"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Neural networks"
    ],
    [
      "plos",
      "/Computer and information sciences/Neural networks"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Probability theory/Markov processes"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Statistics/Markov processes"
    ],
    [
      "plos",
      "/Physical sciences/Physics/Electricity"
    ],
    [
      "plos",
      "/Research and analysis methods/Research assessment/Reproducibility"
    ],
    [
      "plos",
      "/Social sciences/Economics"
    ],
    [
      "plos",
      "/Social sciences/Economics/Finance"
    ],
    [
      "plos",
      "/Social sciences/Political science/Public policy/Taxes"
    ]
  ],
  "openalex": "W7215103402",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0353137&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/a9ep0cnzxth9r.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:37Z",
      "native_id": "10.1371/journal.pone.0353137",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0353137"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:cell biology",
      "subfield": "cell-biology"
    },
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    },
    {
      "field": "mathematics",
      "origin": "plos:probability theory",
      "subfield": "probability"
    }
  ],
  "title": "A mechanism-guided simulation framework for synthetic tax-risk data: Constraint validation and reproducible benchmarking",
  "title_text": "A mechanism-guided simulation framework for synthetic tax-risk data: Constraint validation and reproducible benchmarking",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:37Z",
  "url": "https://research.draconitic.com/paper/a9ep0cnzxth9r",
  "venue": "PLOS One",
  "versions": []
}