A hybrid GPR-HS framework models volatilities via univariate Gaussian processes with Matern 5/2 kernel and correlations via historical covariance, with Aggressive Noise Initialization for stability, achieving high regulatory compliance on seven global equity indices over 2020-2025.
Market Risk Assessment of a trading book using Statistical and Machine Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.RM 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Hybrid Gaussian Process Regression Framework for Stable Volatility-Covariance Estimation: Evidence from Global Equity Indices
A hybrid GPR-HS framework models volatilities via univariate Gaussian processes with Matern 5/2 kernel and correlations via historical covariance, with Aggressive Noise Initialization for stability, achieving high regulatory compliance on seven global equity indices over 2020-2025.