Concept · Stock-level risk (bottom-up)
Residual
The part of a stock's return left after the factor model is removed. RiskModels emphasizes the residual as where selection skill lives.
In depth
After the orthogonal cascade strips market, sector, and subsector, what's left is the residual — the pure idiosyncratic bet, where selection skill lives. RiskModels treats the residual as the thing worth measuring, not a leftover.
Formula
ε_i = r_i − Σ_k β_ik · f_k
Compute it with the API
GET /api/metrics/{ticker}
# pip install riskmodels-py
client.get_metrics("NVDA", as_dataframe=True)["l3_residual_er"]In the methodology
Explained risk: variance decomposition →Referenced by (7)
- Every Position Has a Level Too
How RiskModels picks the right hedge depth automatically, per stock, per day
- NVIDIA: The Economic-Profit Burden of an AI Bottleneck
A RiskModels.app visual case study in market-implied expectations
- Decile One, Not Ticker by Ticker
Server-side rank screening turns the universe into one queryable cross-section
- Cascade Hedging and the Cost of Interpretability
Subsector ETF value, joint optimization, and executable hedge layers across 9,074 US mutual funds
- Custom benchmarks for 13F portfolios: relative performance and what they cost to trade
Evidence from 13F filings: Berkshire Hathaway, Pershing Square, Tiger Global, Lone Pine and Baupost, plus 2,801 filed portfolios and 144 large wealth managers
- RiskModels Quarterly Funds Report — Q1 2026
Top cohort holdings refresh, factor decomposition, and residual winners for the March 2026 reporting window
- Who got NVDA right before it became benchmark exposure?
Early ownership, active conviction, and residual attribution in U.S. mutual-fund managers, 2019–2026