📈
Market Regime Scorecard
A Hidden Markov Model (HMM) classifier that labels the current market state as risk-on, risk-off, or neutral based on multi-factor inputs.
Signal Quality
| Period | Accuracy | Samples | Significance |
|---|---|---|---|
| 7d | 71% | 2,016 | ✅ Significant |
| 30d | 68% | 8,640 | ✅ Significant |
| 90d | 66% | 25,920 | ✅ Significant |
Calibration: Accuracy = % of time the predicted regime matches the realized 4h price direction. Buy → positive return, Sell → negative return.
Current Reading
Current Value
0.7476
alpha_regime_prob
Methodology Version
v3.0 (2026-02)
Current regime probability vs historical confidence distribution.
24h History
500 data points · alpha_regime_prob
Strengths & Weaknesses
✅ Strengths
- Integrates multiple signal factors
- Good at identifying trend persistence
- Low false-positive rate
Best regime: trending (either direction)
⚠️ Weaknesses
- Slow to switch during rapid reversals
- Regime transitions are detection, not prediction
- 3-5min latency
Worst regime: choppy / whipsaw markets
Methodology Changelog
| Date | Version | Change |
|---|---|---|
| 2026-02 | v3.0 | Upgraded to 3-state HMM with cross-asset inputs |
| 2025-10 | v2.0 | Added volatility regime as HMM input |
| 2025-05 | v1.0 | Initial 2-state HMM (risk-on/risk-off) |
Related
Don't just stare at the dashboard. Automate it.
Every metric on this page is available via our sub-millisecond API.
Build trading bots, backtest strategies, and power AI agents with institutional-grade data.