Skip to content
Research
KnowledgeVisuals
Pricing↗Open the workspace↗Get a free API key↗
.orgResearchResearch — current site.netWorkspace↗Workspace — opens riskmodels.net.appAPI↗API — opens riskmodels.app
Next filing · Form 10-Q · Q2 2026 · 2 days
Next filing · Form 10-Q · Q2 2026 · 2 daysMethodology Paper · Part III published: The One Manager Skill That PersistsAPI Update · Point-in-Time (PIT) historical commit tracking — securities and funds unifiedAPI Update · ERM3 L3 variance partition — institutional transparency releasePart 3 · The Persistence of Stock-Selection ResidualsPart 1 · One Position, Four BetsNext filing · Form 10-Q · Q2 2026 · 2 daysMethodology Paper · Part III published: The One Manager Skill That PersistsAPI Update · Point-in-Time (PIT) historical commit tracking — securities and funds unifiedAPI Update · ERM3 L3 variance partition — institutional transparency releasePart 3 · The Persistence of Stock-Selection ResidualsPart 1 · One Position, Four Bets
Ledger
    • Cascade Hedging and the Cost of Interpretability
    • Decile One, Not Ticker by Ticker
    • Every Position Has a Level Too
    • NVIDIA: The Economic-Profit Burden of an AI Bottleneck
    • RiskModels Quarterly Funds Report — Q1 2026
    • The Industry Beneath the Index
    • When does a spin-off start having returns?
    • Who got NVDA right before it became benchmark exposure?
  • Visuals
    • Concept graph (all)
    • Public glossary
  • Methodology
    • Filing calendar
    • API use-cases
    • Pricing↗
    • About

Concept · The RiskModels engine (ERM3)

Hierarchical cascade (L1/L2/L3)

L1 = market (SPY); L2 = sector ETF (e.g. XLK) fit on the L1 residual; L3 = subsector ETF (e.g. SOXX) fit on the L2 residual. Each level explains what the prior one left over.

In depth

L1 fits market (SPY); L2 fits the sector ETF on what L1 left over; L3 fits the subsector ETF on what L2 left over. Each level explains only its incremental risk, so the shares are additive.

Formula

r = β_m·r_m (L1) → β_s·r*_sector (L2) → β_u·r*_sub (L3) → ε

Compute it with the API

POST /api/decompose

# pip install riskmodels-py
client.decompose("NVDA")

Full API docs ↗

In the methodology

The three levels: L1, L2, L3 →

Referenced by (1)

  • Cascade Hedging and the Cost of Interpretability

    Subsector ETF value, joint optimization, and executable hedge layers across 9,074 US mutual funds

Related concepts

ERM3Link beta (λ)Explained risk (ER)Replication equationRobust beta (Huber-M)Vasicek shrinkageL-star ruleGeometric attribution bridgeResidual mean-reversion signal
← ERM3The RiskModels engine (ERM3) · 2 / 10Link beta (λ) →
Get a free API keyRun on your portfolio

RiskModels.org

A research surface for hierarchical orthogonal decomposition, variance attribution, and allocator-grade risk measurement. Operational APIs and developer workflows live at riskmodels.app.

Subscribe to the Quarterly Attribution Review.

Research notes on risk decomposition, fund attribution, 13F filings, and benchmark structure — a few times a quarter.

By registering, you agree to receive technical factor research and API deployment logs. RM-Registry-2026. Privacy Policy.

Sign inHomePrimerWorkspaceResearchKnowledgeConceptsReviewsLedgerReferencesAboutSubscribeMethodology noteOne-pagerAPI docsWeb appContactPrivacyStatusRSS
RiskModelsResearch/Workspace/API