Stability Features
Time-series stability diagnostics. These FeatureTypes measure how a signal behaves over time — autocorrelation decay, half-life, turnover, and term structure.
| Feature | Category | Description |
|---|---|---|
| autocorrelation | statistics | Autocorrelation of any input signal at specified lag — measures signal persis... |
| consecutive_above_threshold | statistics | Duration of consecutive observations above a threshold — measures regime pers... |
| liquidity_recovery_half_life | order_flow | Half-life of liquidity recovery after stress — time for depth to recover from... |
| order_flow_autocorrelation | order_flow | Order flow autocorrelation: corr(ofi, prev(ofi, 1), window=20) |
| range_expansion_rate | momentum | Rate of price range expansion — measures whether volatility is expanding or c... |
| rolling_volatility_of_volatility | volatility | Rolling volatility of volatility: rolling_std(vol_of_vol) — measures stabilit... |
| signal_half_life | statistics | Half-life of signal persistence — time for signal to drop below threshold |
| signal_turnover | statistics | Signal turnover: fraction of signal direction flips per window — low turnover... |
| volatility_term_structure_slope | volatility | Slope of volatility term structure — measures how vol decays with time scale |