Regime
HSMM Regime Detection
Identify structural market regimes and how long they tend to persist.
Status beta · Version 0.3 · Sep 2026
P(Xₜ₊₁ | Xₜ)
Illustrative distribution, not a live forecast.
Bull 34%
Neutral 41%
Bear 25%
Overview
A hidden semi-Markov model treats the market as a small set of latent regimes with explicit duration, instead of a single stationary process.
Figures on this page are model output examples. They are estimated distributions, not a statement of where the market will trade.
How it works
- 01 Observe returns and flow
- 02 Infer latent regime
- 03 Estimate duration
- 04 Publish state and transitions
Inputs
| Asset | BTCUSDT |
| Resolution | 1h |
| States | 3 |
Outputs
- Regime label
- Persistence
- Transition matrix
Model statistics
Published as quality of the estimate. Directional accuracy is not the headline for a probabilistic model.
- Regime persistence
- reported per fit
- Transition accuracy
- OOS
- Stability
- walk-forward
Validation
- Walk-forward
- OOS significance
Data sources
ArcDelta: trades, order book, open interest, funding, OHLCV.
Access
From Quant plan. Included runs, path limits, and API access follow the Labs tier on the TreVmS account. Individual metrics are not sold separately.