quant research // summarizing the paperLOADING
Ujjwala Vadrevu · 2026-07-06
The paper introduces SHARC, a method that uses SHAP (a game-theory-based explanation tool) to make a machine-learning risk model (Hybrid Gaussian Process Regression) explainable for regulators. It applies this to Stressed Value-at-Risk under three hypothetical macro scenarios and breaks the capital estimate into baseline, mean-return, and volatility components. It reports that the framework reliably traces capital outputs back to scenario inputs, and that directional loss (mean return) matters more than volatility in setting stressed capital levels.
Why it matters: Practitioners in bank risk, regulatory capital, and stress testing might care because it addresses the 'black box' obstacle to using ML models under ICAAP/CCAR/FRTB. The finding that directional loss dominates volatility in stressed conditions could inform how limits, positioning, and hedging are calibrated during severe scenarios.
⚠ This is a framework demonstration for institutional regulatory capital using specific hypothetical scenarios and a particular model, not a validated, real-world profit or general-investing tool.
The adoption of non-parametric machine learning models for regulatory capital estimation introduces a fundamental governance challenge: the inability to explain model outputs in a manner auditable by supervisory bodies. This 'black box' problem remains a major barrier to the adoption of Gaussian Process Regression (GPR) and related ML architectures in ICAAP and CCAR workflows despite their predictive advantages over traditional parametric approaches. This paper addresses this barrier through SHARC (SHAP for Regulatory Capital), an explainability framework for the Hybrid GPR-HS architecture and its stress-testing extension. SHapley Additive exPlanations (SHAP), derived from cooperative game theory and satisfying the properties of Local Accuracy, Missingness, Consistency, and Efficiency, are applied to Stressed Value-at-Risk (SVaR) outputs under three macro scenarios: West Asia War, Climate Risk, and AI Bubble/Regulatory Burden. SHARC decomposes SVaR into baseline, mean-driven, and volatility-driven components, enabling transparent linkage between scenario design and capital outcomes. Two findings emerge. First, SHARC consistently links non-linear SVaR outputs to underlying scenario inputs, confirming framework fidelity and providing auditable traceability of capital drivers. Second, under stress conditions, the mean return component (directional loss magnitude) dominates the variance component (volatility baseline) in determining capital levels, with implications for capital limit-setting, position management, and hedging strategy. The results establish SHARC as a regulator-aligned explainability layer that makes the Hybrid GPR-HS framework fully auditable and consistent with FRTB, ICAAP Pillar 2, and CCAR transparency requirements.
Go deeper: a full research-committee breakdown of this paper, its assumptions and failure modes, and how its method would apply to a specific ticker or your watchlist. See StockTools AI →
AI summary generated from the paper’s public abstract via arXiv; it may miss nuance — read the source before relying on it. Thank you to arXiv for its open-access interoperability; StockTools is not affiliated with arXiv, and all rights remain with the authors. Educational only, not financial advice.