Portfolio Covariance & VaR Engine

Compute Historical, Parametric (variance-covariance), and Monte Carlo Value-at-Risk (VaR) and Expected Shortfall (ES/CVaR) across a synthetic portfolio of up to 500 assets. JS-parallel Cholesky-decomposed correlated returns. Configurable confidence level, holding period, and sector structure. Buy-side zero-egress story — all computation in the browser. Client-side. Zero PII.

AP2 Export Chains: SIM-03 JS Parallel · Cholesky VaR · ES · 3 Methods Zero PII · Zero Egress

🔒 Synthetic portfolio. No real positions or PII. Runs entirely in your browser — zero data egress.

⚠ Educational/simulation only. VaR and ES are statistical estimates on synthetic return data. Not for regulatory reporting or investment decisions.

Portfolio configuration

Number of assets

Portfolio value (USD millions)

Monte Carlo simulations

VaR confidence level

Holding period (days)

Sector composition

Avg correlation (ρ)

VaR & ES summary

Approach comparison (Historical vs Parametric vs Monte Carlo)

P&L return distribution (Monte Carlo)

Covariance matrix sample (first 8 assets)

Chain to SIM-03

→ SIM-03 Basel RWA Modeler