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

Ask your agent

Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.

Run the AINumbers MCP tool `compute_portfolio_var`. Task: Compute Historical, Parametric, and Monte Carlo VaR and Expected Shortfall across a synthetic portfolio.
Call it with arguments: {"policy_parameters":{"n_assets":2,"n_paths":100,"conf_level":0.975,"correlation":0.3,"holding_period":10,"seed":42}}
Verify before trusting: this node computes in your browser, so the MCP endpoint returns no execution_hash. Run the tool in the page, export the Policy Mandate artifact it produces, and call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with that artifact.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/qfa-02-portfolio-var-engine.html#p=v1.H4sIAAAAAAAA_wFfAKD_eyJuX2Fzc2V0cyI6Miwibl9wYXRocyI6MTAwLCJjb25mX2xldmVsIjowLjk3NSwiY29ycmVsYXRpb24iOjAuMywiaG9sZGluZ19wZXJpb2QiOjEwLCJzZWVkIjo0Mn2tyKsXXwAAAA