Methodology
What the TradeMachine Score is
A ranking metric on a 0–100 scale, combining nine weighted components: technical alignment (18%), regime alignment (15%), liquidity (15%), volatility edge (15%), probability quality (12%), historical setup edge (10%), risk/reward (8%), event-risk quality (4%) and data-quality confidence (3%). It orders candidates against each other. It is not a probability of profit, a forecast, or a win rate.
Estimated vs. realized
Estimated probability of profit is a model output derived from a log-normal terminal-price model. Historical setup win rate is measured from recorded outcomes of comparable past setups and is always shown with its sample size. Realized strategy performance is tracked separately. These are never combined into a single figure, and backtested, paper and live results are never merged.
When the platform publishes nothing
A candidate is rejected outright if market data is stale, a market is crossed, liquidity is below threshold, the regime is incompatible, an event exclusion applies, or a daily quota is met. A day with no published signal is a valid and intended outcome.
Reproducibility
Every published signal stores the inputs it was derived from, a SHA-256 hash of those inputs, and the versions of the strategy, score and regime model used. Published signals are immutable; all subsequent lifecycle activity is recorded as separate events.
Risk disclosure
This platform is an educational and research tool. It does not provide investment advice or personalized recommendations. Options trading involves substantial risk of loss and is not suitable for every investor. No result shown here is a guarantee of future performance.