EcoStack-Pro: an adaptive federated learning framework for interpretable ESG auditing across heterogeneous industrial sectors

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

🔬研究者:This paper contributes a novel federated learning architecture with adaptive weighting and interpretability methods for cross-sector ESG auditing.

🏢実務担当者:Corporate sustainability teams can adopt this framework for secure, high-accuracy ESG audits across diverse business units or supply chains.

🏛政策担当者:Policymakers may consider this as a model for privacy-preserving mandatory ESG disclosure verification.

Introduction The paradigm shifts toward environmental, social, and governance (ESG) metrics has necessitated advanced auditing systems capable of analyzing complex, non-financial performance indicators. However, traditional centralized artificial intelligence (AI) models conflict with increasingly stringent data privacy regulations, while conventional federated learning approaches struggle to converge under the high statistical heterogeneity and data imbalance typical of diverse industrial sectors. Methods To address the trade-off between high-precision forecasting and data sovereignty, this study proposes EcoStack-Pro, a decentralized auditing framework driven by a stacked ensemble of LightGBM, XGBoost, and Gradient Boosting regressors, optimized via a Bayesian ridge meta-learner. Central to this architecture is the Fed-GenAdaptive algorithm, which employs a soft-gating mechanism with softmax normalization to dynamically weight client contributions according to their local validation errors and generalization gaps. Results Utilizing a stratified dataset of 21,400 firm-year observations across 10 distinct industrial clients, the framework achieves a test-set R2 of 0.9614. This performance retains 98.2% of the predictive power of the centralized upper bound (R2 of 0.9790) while strictly preserving corporate privacy. Discussion Furthermore, the integration of Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) enhances model interpretability, elucidating the non-linear drivers of governance ratings. These results demonstrate that adaptive, diverse ensemble strategies can overcome the limitations of single-model federated baselines, providing a robust framework for secure, cross-sector sustainable finance auditing.

• semanticscholar https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2026.1813511/pdffirst seen 2026-07-19 05:57:34