Cross-asset relationships describe how different assets behave in relation to one another. In quantitative strategies, rolling correlations and spreads turn these relationships into predictive features that can capture market dynamics missed by single-asset indicators. section 10.4.2
A practical feature-engineering workflow:
- Calculate returns for selected assets, then use rolling windows to compute pairwise correlations and cross-asset spreads. section 10.4.2
- Check how features behave together: liquidity- or volatility-weight composite signals when appropriate, and inspect feature-correlation matrices for redundancy. section 10.4.3
- Treat apparent relationships cautiously: correlations can shift or break during crises, and relationships that look robust may fail in real markets. section 10.4.2 section 10.4.3
Table 10.3 Feature categories for institutional-grade strategies
|
Category
|
Purpose
|
Examples
|
Quant insight
|
|---|---|---|---|
|
Cross-Asset Signals
|
Capture regime shifts
|
SPY-TLT correlation, CBOE Volatility Index (VIX)-equity spreads
|
Relationships break during crises.
|
|
Momentum Cascades
|
Multiple time frame trends
|
5d versus 20d momentum divergence
|
Short-term reversals cause long-term persistence.
|
|
Volatility Regimes
|
Risk environment
|
VIX term structure, realized volatility clustering
|
Volatility predicts volatility and affects correlations.
|
|
Economic Proxies
|
Macro factor exposure
|
Dollar strength versus emerging markets (EM), commodity momentum
|
ETFs are used as real-time economic sensors.
|
Compare cross-asset signals with other feature categories, including examples and cautions about regime shifts. section 10.4.2
