Blog/Research & Analysis
Research notes · provenance-first

Plain-language analysis of deployed models.

Every note ships with the model card, feature attribution, calibration plot, and the timestamped forecasts it was generated against.

50articles
15archetypes
2asset classes
50 of 50 articles
Title
The Kurtosis Archetype: trading the tail weight of a seriesReusable method · applies across assets
How a jumpiness rule traded a tripling INTC and came up just shortequity
Why a selective momentum model trailed ASTS's runaway trendequity
How a volatility-regime model rode ARM both ways and still trailed the stockequity
How a consensus model chased ARM's climb and finished a step behindequity
Why a trend-vote model turned a profit while COIN went nowhereequity
The Channel Breakout Archetype: following a move beyond a self-scaling bandReusable method · applies across assets
The Disorder Archetype: acting when a reading scatters beyond its normal rangeReusable method · applies across assets
The Divergence Archetype: acting when two readings begin to move apartReusable method · applies across assets
The Long-Memory Archetype: when a reading keeps its direction, or keeps reversingReusable method · applies across assets
The Momentum Agreement Archetype: when timescales must agreeReusable method · applies across assets
Why a volatility-regime model lost more often than it won on QBTS and still made moneyequity
The Open-Interest Positioning Regime Archetype: reading where the options crowd is positioned, not the price, to infer directionReusable method · applies across assets
The Put-Skew Regime Archetype: trading the price of fear, when it is overdone and when it is earnedReusable method · applies across assets
The Volatility Surface Archetype: reading the shape of the options surface, not the price, to infer directionReusable method · applies across assets
The Z-Score Reversion Onset Archetype: standardizing a market-state input, and acting on the turn rather than the extremeReusable method · applies across assets
The Correlation-Signal Archetype: reading one move through another, until the link breaksReusable method · applies across assets
The Signal-Ensemble Archetype: how a Composite Predictive model trades agreement, not any one inputReusable method · applies across assets
The Volatility-Regime Reversion Archetype: Fading a Deviation Only When the Volatility Regime Supports ReversionReusable method · applies across assets
How a disorder-regime model split even on LUNR and still trailed the stockequity
How a tail-shape rule traded HPE to a near dead heat with the stockequity
How CIEN's tail-extreme model caught the run, and a buy-and-hold caught moreequity
Why a persistence-filter model demanded confirmation on IREN and banked under half the runequity
The Conditional Z-Score Archetype: Standardizing a Market State and Trading Only When a Gate AgreesReusable method · applies across assets
How a tail-weight rule won three of four trades yet trailed SNDK badlyequity
Why a kurtosis model caught only part of HOOD's big runequity
How a volatility-regime model traded HOOD long most of the time and banked under half the runequity
How a disorder-regime model rode CIFR's calm patches and skipped the restequity
Why a tail-fattening rule caught only a sliver of MU's runequity
How a return-shape rule traded STX and held patiently for weeksequity
Why a disorder-regime model traded AAOI and missed the runequity
How a breakout model traded CRWD and finished ahead of the stockequity
How a sticky-threshold regime model beat a falling COIN by staying long and selectiveequity
How a channel-breakout model edged past INTC by trading both sides of the moveequity
How a kurtosis model traded DELL to a near dead heat with the stockequity
How a trend-consensus model nosed ahead of holding TSLAequity
How a stacked-trend model profited as CRWV slid lowerequity
How a two-sided model beat a falling NKE on a razor-thin edgeequity
How a Hurst-regime model read BE as trending, traded it long, and still trailed a huge runequity
Inside QBTS's open-interest positioning gate: 66 trades, a failed drawdown limit, and a trailing benchmarkequity
How a condition z-score rule traded both sides of MDB's sharp swings in backtestequity
How a consensus model traded PLTR and skipped most of the rallyequity
How a divergence model fought TSLA's moves both ways and edged ahead of the stockequity
How a channel-breakout model traded VRT fast and often, and still trailed the stockequity
How a condition z-score rule traded BE through an eighteenfold climb in backtestequity
How a condition z-score rule traded both sides of HOOD's big run in backtestequity
The Percentile-Regime Archetype: Ranking a Market State to Decide When to Go Long, Short, or Stand AsideReusable method · applies across assets
How a percentile-regime model reads BTC and when it stands aside
How a composite predictive signals model traded ETH 94 times and missed four gates
Bid-Ask Imbalance: Volume-Weighted Spread Changes as Trading Signals
Transparent. Probabilistic. Built for real decisions.

Every note links to the deployed model card, the feature attribution, and the live forecast log.

Read our methodology  ↗