Quant stack

Methodology

This page explains how the WDI pre-match stack thinks — layer contracts, core pricing algorithms, and the publish surface. The website is explanatory and read-only: it does not run the engine in the browser.

Pricing chain (final matrix) Cθ(Fν(λ), Gν(μ)) →IPFcurrent →1X2 / EV opening →COM-Poisson+Frank invert (ν=1 then re-fit at final ν) · physics · Copula · current IPF

Layer contracts

Two compute layers feed an immutable publish layer. Boundaries are intentional — so fundamentals never silently become prices.

L2 · FUNDAMENTALS

Geo / SKILL / Ensemble

Geo-kinetic priors and optional XGBoost residuals produce xGF / xGA only. Modes: geo (primary), residual, or ensemble. Reports show the skill_mode that was used — L2 never prices 1X2.

L1 · PRICING

Physics · Copula · EV

Match physics synthesizes intensities (λ, μ); COM-Poisson ν shapes scoring tails on the final joint matrix. Frank Copula couples the sides; IPF soft-anchors to current de-vigged margins; tri-track EV selects ANCHOR / ALPHA / ROCKET.

PUBLISH

Immutable slate

Board, per-match JSON, and posters are frozen artifacts. Free: 1X2 bands + track presence. Pro: picks, scorelines, λ/μ, and fundamentals context.

Core pricing algorithms

The six ideas that define WDI pricing — what each does, and what it deliberately does not do.

Joint scorelines

Frank Copula

Links home and away goal counts into one joint scoreline matrix — not two independent Poissons glued together. Dependence strength θ is shared between opening-market invert and the final matrix build.

Does not: invent 1X2 from XGBoost directly.

Tail control

COM-Poisson ν

On the final matrix, asymmetric ν controls how fat or thin each side’s scoreline tails are under chaos, fatigue, or cup context — before the Copula couples the sides. Opening invert and the joint matrix share the same COM-Poisson marginal helper; when market-anchored, λ/μ are re-fit under the final ν so margins stay consistent.

Does not: replace the Copula joint step.

De-vig

Shin · Power

Shin removes bookmaker overround on 1X2; Power de-vig covers Asian handicap and totals (and is the Shin fallback). Cleaned market probabilities feed IPF and EV comparison — model 1X2 itself still comes from the Copula matrix, not from the book sheet alone.

Does not: claim every book is a sharp reference, or replace model pricing.

Soft coupling

Market anchor η

When opening 1X2 + totals imply λ/μ (COM-Poisson+Frank invert; first pass ν=1), physical modifiers are η-blended toward that market base. After final ν is set, λ/μ are re-calibrated under that ν so invert margins match the Copula build.

Does not: hard-overwrite λ/μ with raw book prices.

Market margins

IPF blend

Iterative Proportional Fitting gently reshapes the Copula matrix toward de-vigged current 1X2 and totals margins when those lines are present — soft blend, audited weight. Opening is used for λ/μ anchoring; current is used for IPF.

Does not: discard the model matrix for a pure market sheet, or IPF from opening alone.

Value tracks

Tri-track EV

ANCHOR is the production spine; ALPHA hunts medium-volatility value; ROCKET is high-volatility research. Confidence stars are a recommendation index — not a stake %.

Does not: show Kelly % or bankroll advice on this site.

Pipeline

  1. Fundamentals — Geo-kinetic and optional SKILL residual →home & away xGF, xGA.
  2. Match inputs — Publish may apply Virtual Elo (travel / altitude) upstream; L1 then uses Elo priors, travel tax, and intensity for spear / shield.
  3. Opening invert — Opening 1X2 + totals →COM-Poisson+Frank implied λ̂, μ̂ (ν=1 first pass; re-fit at final ν when anchored).
  4. λ / μ synthesis — Asymptotic squash and η soft-coupling of physics onto the market or geo base.
  5. COM-Poisson ν — Asymmetric tails for the joint matrix; shared marginal helper with market invert.
  6. Frank Copula — Joint scoreline matrix from λ (home) and μ (away) with shared θ.
  7. IPF / current margins — Soft blend toward de-vigged current 1X2 and totals when available.
  8. Tri-track EV — ANCHOR (primary), ALPHA (value), ROCKET (high-volatility research).
  9. Publish — Immutable board, report JSON, and posters. Offline / replay mode ships historical showcase dates until live day-ingest is wired (no T−60m live SLA claim).
Match physics (supporting layer)

These modifiers shape λ/μ before Copula pricing. They prove the stack is not a pure market classifier — and when an opening anchor is present they are η soft-coupled, not hard overrides.

Virtual Elo

Applied upstream in publish (flight / altitude) before L1 sees the match. Floor at 1000. When travel_km > 0 is applied here, that side sets travel_distance_via_elo so L1 tax does not re-count km.

Travel tax

Separate L1 channel: timezone, rest, and age logistics. Distance km is included only when Virtual Elo did not already own that side’s flight distance.

HOME_ADV

League-aware home boost on intensity. When market-anchored, blended with η instead of full override.

Asymptotic squash

Tanh-bounded growth / decay on λ and μ so extreme priors cannot explode the scoreline grid.

EEM · depth · logistics

Error-exploitation multiplier, squad-depth elasticity, and recovery ψ — favorite pressure and fatigue nuance.

Formation topology

Spear / shield counters from formation pairs. Often off for club leagues until formation ingest is trusted.

Physics explains intensity — it does not replace Frank Copula, IPF, or tri-track selection.

Tri-track Layer A

Three research weights on the same fair matrix — not three equal stake recommendations.

Track Win preference Volatility Product weight
ANCHOR Favors high model win probability · production spine Low–medium Primary
ALPHA Ranks by EV × win probability · value hunt Medium Secondary
ROCKET Contrarian / smart-money · EV & skew gates High Research only

Confidence stars are a recommendation index, not a stake instruction. Half-Kelly exists only as an internal ceiling for stars and portfolio caps — never shown as a bet size.

What this stack does not do

  • L2 never outputs 1X2 prices or replaces Copula / find_ev.
  • This website does not execute the model live — it explains and displays published research.
  • No Kelly stake % or bankroll advice appears on the product surface.
  • Soft-book closes are not silently labeled as Pinnacle CLV — the Odds chip states the reference.
  • Dixon–Coles low-score tweaks are legacy research only — production pricing is Copula-first.

Odds reference honesty

Published fixtures often carry soft-book closing prices. CLV figures stay labeled soft-book until a Pinnacle (or mixed) reference is present on the artifact. Hub and Report surfaces show an Odds chip so the reference is never ambiguous.

Display 1X2 vs value-bet book

Under the default calibration policy (display_only / ADR-0015), on-screen 1X2 bars may use calibrated margins while ANCHOR / ALPHA / ROCKET value bets always price from the joint score-matrix margins. Published reports expose pricing_1x2 (matrix) beside display prob_*, plus a physics_audit block (market-anchored flag, η, favorite side).

Score-matrix UI slice

Top scorelines use the full 16×16 joint. Any UI heat grid is an 8×8 slice — under fat tails the visible mass can sum to less than 1 without implying a bug.

Open Intelligence Hub View tiers