mlsanityData to 7 Oct 2026

PaGNet: A Panel-Aware GBDT--Neural Network for Multi-Target Corporate Tax Avoidance Proxy Forecasting

arXiv 2609.20177 ↗First posted 24 Jul 2026cs.AI cs.CE cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Forecasting corporate tax avoidance proxies from firm--year panel data is challenging because predictive signals are distributed across short firm histories and related targets, while screening-oriented use requires transparent model behavior. We propose PaGNet (Panel-Aware GBDT--Neural Network), a two-branch hybrid that combines a LightGBM branch using panel-temporal summaries with a Panel-MLP branch using attention-pooled temporal aggregation and shared-trunk multi-task learning. A per-target validation-optimal blender produces both the final prediction and a compact branch-reliance diagnostic without trainable fusion parameters. On the KoTaP panel of 1,754 Korean listed firms from 2011--2024, PaGNet is evaluated under a leakage-free, shared-hyperparameter protocol across four feature regimes. In the direct-proxy-lag-excluded FS1 regime and the tax-history-augmented FS2 regime, accrual targets (TSTA, TSDA) route stably to the LightGBM branch, where PaGNet raises explained variance over the strongest of six baselines by roughly 0.08--0.11 on the primary split. GETR often leans toward the neural branch, while CETR exposes a validation--test branch-selection mismatch rather than a stable branch assignment. A panel-flatten control shows that most accrual gains come from observed multi-year base-panel values, with PaGNet's panel-aware representation adding a smaller but directionally consistent refinement. Rolling-origin analysis confirms stable accrual routing, bounds ETR diagnostics to split-specific behavior, and identifies a far-horizon split where supervised models underperform naive persistence. PaGNet is therefore best viewed not as a universally superior tabular learner, but as a proxy-aware panel model that combines competitive forecasting with explicit per-target branch-reliance reporting.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 47 references that are in the map. First posted on arXiv 24 Jul 2026.

Builds on

15 of 47 references.

References · 15

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  3. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  4. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 748
  5. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  6. 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
  7. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 398
  8. 2018CatBoost: gradient boosting with categorical features supportcited by 208
  9. 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 200
  10. 2023ExcelFormer: A neural network surpassing GBDTs on tabular datacited by 33
  11. 2020Transparency, Auditability and eXplainability of Machine Learning Models in Credit Scoringcited by 26
  12. 2022Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Modelscited by 12
3 more
  1. 2023Blending gradient boosted trees and neural networks for point and probabilistic forecasting of hierarchical time seriescited by 5
  2. 2024Team up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPscited by 3
  3. 2025KoTaP: A Panel Dataset for Corporate Tax Avoidance, Performance, and Governance in Koreacited by 1

Built on by

Not cited yet.