Market Sentinel computes a structural regime for any asset relative to a reference benchmark. The core measurement is the ratio between the asset's current structural state and its historical anchor — how far it has moved relative to where its structure was committed. This is not a price prediction. It is a structural state classification.
| Regime | Condition | Prediction |
|---|---|---|
| Recovering | α < 0.85 — below structural floor | Recovery outperformance expected relative to reference until structural parity is restored |
| Inflection | 0.85 ≤ α ≤ 1.15 — near parity | No directional prediction. Maximum structural uncertainty. Governed abstention. |
| Trending | α > 1.15 — above structural floor | Continued outperformance expected relative to reference until a structural shock resets the floor |
Inflection calls are excluded from accuracy statistics. They make no directional prediction and cannot be graded correct or wrong.
A call is graded using the 6-month forward relative return of the asset vs its reference benchmark, measured from the call date.
These are historical replay results, not live managed-account results.
Each call is reconstructed from point-in-time archived data: the engine is run as it would have run on that date, using only data available on that date. No future data is used in constructing any historical call. The calls are generated forward-in-time and graded against subsequent market outcomes — they are not fitted to outcomes.
Results on the track record page reflect the engine as deployed at the time of each backtest run. Methodology changes are versioned; prior published stats reflect prior methodology versions.
The following tickers are excluded from accuracy statistics. Exclusion rules are fixed in the methodology and applied uniformly — they are not selected to improve reported accuracy.
Country ETFs denominated in USD but tracking non-USD markets (INDA, EWJ, EWZ, VGK, FXI, EWT) embed two structural floors: the local equity structure and the USD/FX rate. The floor assignment is invalid under the floor selection theorem — the structural prediction has no basis when the reference belongs to a different currency domain. These are flagged as out-of-domain, not wrong calls.
Full exclusion criteria and floor selection methodology are documented in the methodology page.
Indian IT stocks (TCS.NS, INFY.NS, WIPRO.NS) are excluded because they are major constituents of their benchmark (ITBEES). The benchmark drifts with the stock, making the structural floor invalid. This is benchmark contamination, not model failure.
Indian conglomerate tickers with known structural breaks (ADANIENT.NS post-Hindenburg, ITC.NS under regulatory pressure) are excluded after the break event date. The structural floor does not survive the break.
TATAMOTORS.NS excluded: data unavailable from source during audit period.
Wrong calls are included. All correct calls are included. All ambiguous calls where the outcome was within the noise floor are excluded by the noise-floor rule above (uniformly applied). No calls are excluded because they were wrong.
Every analysis is relative to a reference. The reference is fixed per ticker and is the same for all users:
| Asset class | Reference | Rationale |
|---|---|---|
| US equities | Sector ETF (XLK, XLF, XLY…) | Same-sector floor isolates stock-specific structural divergence from sector drift |
| India equities | Sector Bees ETF (NIFTYBEES, BANKBEES, ITBEES) | Local-market, local-currency floor |
| Crypto | USD (BTC/USD, ETH/USD) | USD as settlement reference |
| Gold/Silver | GLD/SPY or SLV/GLD | Commodity vs equity or precious metals relative structure |
| Fixed income | Duration-matched benchmark (TLT/IEF, HYG/LQD) | Duration or credit differential isolates rate/credit structural signal |
| Currency | Cross-rate pair (EUR/JPY, GBP/EUR…) | Relative monetary structure, not USD-absolute |
The structural regime framework derives from the structural parity variance equation:
σ² = k / (α − 1)²
Where σ² is variance, α is the ratio between current and historical structural state, and k is the domain noise floor constant. The singularity at α = 1 defines the Inflection zone — maximum structural uncertainty, no directional prediction. This equation is validated across five independent domains spanning 18 orders of magnitude (R² ≥ 0.981 in each domain). These domains were not selected to fit the framework; validation was conducted on existing published datasets.
The five validation domains: financial markets, ENSO climate cycles, seismic activity, biological regulatory networks, plasma physics.
For informational purposes only. Not financial advice. Structural regime signals are probabilistic indicators, not predictions of future performance. · Full call log · Demo · Plans