Loading live data…Loading live data…Loading live data…

Methodology

How we model
the market.

Most services flash their wins and bury their losses. We do the opposite. Here is exactly how Blitzen turns raw market data into models — and the honest record of what they do and don't beat.

NBA · CLOSE PROJECTIONMODELING
ConsensusSharp bookModel projection▲ projecting the close
15
leagues tracked
~40
sportsbooks
5+
seasons of odds
Walk-forward
validation only

The pipeline

From raw market
to a graded edge.

A model is only as honest as the path that built it. Ours is one straight line — and the same feature code runs at training time and at serve time, so what we test is what you get.

01

Ingest

~40 sportsbooks via The Odds API + ESPN / nflverse stats, every line since it opened.

02

Engineer

Team form, pace, EPA, injuries, weather, and market-structure features — built once, identically for train and serve.

03

Train

Gradient-boosted trees per market, walk-forward by season — trained only on the past.

04

Validate

Score on seasons the model never saw. No leakage, no cherry-picking, bootstrap confidence intervals.

05

Gate

Only models that clear the closing-line-value bar are allowed to call themselves production.

06

Serve

The survivors run live in the terminal — every prediction stamped with its honest track record.

The analysts

Three specialists,
one market each.

We don't run one black box that does everything. Each market gets a specialist, trained on the features that actually move it — and each carries its own honest status, never a borrowed one.

Marlon

Live

Moneyline

Picks winners from time-bucketed line snapshots, bookmaker disagreement, and team-quality gaps. Calibrated and running live on the NBA and NFL; the college-football model is served as research, not a proven live signal.

NBA: ~64% accuracy · AUC 0.70

Xavier

In tune-up

Spread

Reads the spread from team form, pace, shooting, and market structure. The spread market is sharp at our current feature set — so Xavier stays in tune-up until new signal earns its way back.

Honest status: no edge yet

Clyde

In tune-up

Totals (O/U)

Projects the over/under from offensive pace and defensive efficiency. Walk-forward shows a neutral edge today — so we say so, rather than dress it up.

Honest status: neutral

The architectures we run

XGBoost

Today's workhorse — gradient-boosted decision trees, one per market.

Line-movement transformer

Research

A sequence model that reads how a line moves toward the close, bucket by bucket.

Stacked ensemble

Building

The compound model — validated parts assembled into one interpretable pipeline.

Blitzen meta-model

Planned

A house-and-community meta-model that ranks the whole slate on a unit-safe score.

The scoreboard

We grade ourselves
on the close.

Win rate lies — you can win a coin-flip streak and still be lighting money on fire. The honest scoreboard is closing-line value: did our bet get a better number than the market's sharpest closing price?

Beat the close consistently and you are genuinely ahead of the market. So that is the bar we hold every model to — measured on games it never trained on, with confidence intervals, not vibes.

And the honest headline today: no model beats the close after the vig yet. The signal is real on moneylines; it just doesn't clear the juice on its own. We tell you that on every model — because a tool you can't trust is worse than no tool.

0.350.600.50 coin flip0.52 gate
Close-predictor
NBA · high conviction
0.54
Marlon
NBA · moneyline
0.50
Transformer
NFL · moneyline
0.49
Marlon
NFL · moneyline
0.37

Every bar is measured, never claimed. A model earns the neon proven-edge badge only when it clears 0.52 with positive average CLV on data it never trained on. Today, nothing has — and we say so on every model.

In development

Compounding
small edges.

One model rarely clears the bar alone. But we have validated parts, not hopeful ones — and the compound model assembles them in evidence order, each doing the one job the data says it can. This is the build we are running now.

1Originate

Close-predictor

Nominates the bet and its direction — the only validated, leakage-free CLV engine.

2Confirm

Sharp-book signal

Confirms or vetoes the direction. The strongest mover, but it never originates or sizes.

3Size

Marlon

Sets a fractional-Kelly stake at the entry price. Calibrated, so it sizes — never gates.

Gate

Walk-forward beat-the-close, pinned to Stage 1. Production-eligibility is judged only on the originating engine's closing-line value — the sizing model's numbers can never sneak a model past the gate.

The goal isn't a magic box. It's to compound a few small, proven edges into something that honestly beats the close — and to ship it the same way we ship everything: gated, measured, and labeled with exactly what it has earned.

See the work yourself.

Every model, its features, and its real track record live in the terminal. Free to explore. Backtest any of it against seasons of real odds.