2.79 How a Decision Tree Engineers a New Alpha
A decision tree mines conditional alphas by carving feature space into boxes. It picks each split to maximize a similarity gain and predicts the mean return per leaf. Stop early or it memorizes noise.
Author
ali askar
2.78 From One Tree to Forests to Boosting
One tree is fragile: a small data change flips its top split. Bagging averages many trees to cut variance; boosting fits each new tree to the residual to cut bias. XGBoost and LightGBM are boosting.
2.77 Linear Models' Hidden Symmetry Advantage
Relabel every long as a short and a return model should flip its sign. Linear models get this free through their weights; a tree relearns each split's mirror, so engineer the symmetry back.
1.26 Large Trades Are Insider Trades by Definition
A large order moves price by construction, so it manufactures the move it seemed to predict. Size needs capital and a firm view, which reads like information on the tape, so the market prices large flow as informed because it cannot tell you apart. Read the permanent impact to separate knowing from
1.25 Who Is the Marginal Buyer?
The seller is easy to picture, so everyone narrates the seller after a crash. Price is set at the margin: the question that forecasts anything is who the marginal buyer is, and where they step back.
5.34 Layering Forecasts Across Horizons: Blending on the Markout Curve
Got forecasts on different clocks? Don't pick the biggest. Normalize each to edge-per-second on its markout curve (30 bps/60s = 0.5 vs 2 bps/1s = 2) and average the curves to blend fast and slow edge into one.
5.43 Predictive but Uncorrelated: Alphas That Only Work as Interactions
Volatility predicts the size of a move, not its direction, so it can't trade alone. Multiply it by momentum and it works, until extreme vol gains its own sign, down for equities and up for gold.
5.45 Detecting Wash Trading with an FFT, and Why Your TWAP Needs Random Timestamps
The Fourier transform fails on price but nails a robot, because a wash bot or metronomic TWAP is the clean periodic signal price never is. Bin trades, FFT the counts, and a sharp spike is automation. The catch: your own equal-interval TWAP makes that spike, so randomize it.
5.44 MFT Execution Is Built on HFT Market-Making
The cheapest way for an MFT shop to enter a small position is to act like a market maker: feed your quoting engine a phantom short so it skews and fills you long, collecting the spread instead of paying it.
4.70 Combining Three Weak Alphas on Cointegrated Futures
Three fair-value estimators for an adjacent crude future, each too weak alone: spread EMA, returns beta, cross-book volume. Weight each by one over its error variance and the shared signal survives while the noise cancels.
2.76 The Limits of Linear Models
The clean linear factor model fails because its weights are not constants. Momentum and carry only pay in the right vol regime, and interactions are the one thing a linear model cannot represent.
5.37 Continuous, Event-Driven Trading vs Bar-Based Research
Bar research assumes the clock drives the market. It doesn't, events do. Fixed rebalance times are front-runnable and bars hide execution seasonality. Screen on bars, validate on event-driven sims, trade on events.