Methodology

What we ship — and what we don't

Edge Equation is a data & analytics service. The workbook contains projections, edges, Kelly figures and historical data. We never publish picks, advice, or recommendations. Every row in the workbook is a deterministic mathematical output. The bet is always yours.

Projection model

For each game we project per-team scoring as a weighted blend of three signals:

• Season pace (45%) — full-season points/runs scored / allowed per game.
• Recent form (30%) — same metrics over the last ten games.
• Opponent context (25%) — opposing team's corresponding allowed / scored rate.

Team aggregates use Bayesian shrinkage with k=15 ghost games of league average baseline so early-season noise can't produce inflated team strength after a hot week.

Adjustments stacked on top (MLB)

• Starting pitcher — quality factor from FIP with a 50-IP shrinkage prior. Applied 5/9 of full-game runs and 90% of first-5-innings projections.
• Bullpen — relief-only ERA per team, 150-IP prior. Carries the remaining 4/9 of full-game runs.
• Park factor — multi-year per-venue multiplier (Coors 1.18, Petco 0.92, etc).
• Weather — outdoor games get a temperature-based factor pulled from Open-Meteo at game time.

Every adjustment is recorded in the workbook's Why-This-Edge column so you can see exactly which factors moved a fair value and by how much.

Probability + Kelly sizing

Run totals are modeled as a Negative Binomial distribution parameterized by empirical season variance, not Poisson — MLB run totals are over-dispersed. Win probabilities use a logistic on projected margin, with the slope fitted from backtest residuals each run rather than hardcoded.

The workbook's Kelly column is half-Kelly by default, capped at 5% of bankroll per play. The Bankroll Manager tab lets you override the fraction and the cap. Every unit suggestion recalculates from your settings — not ours.

Market gating (the hard rule)

A market appears in the workbook's Projections tab only if its rolling 200+ bet backtest shows ≥+1% ROI AND Brier < 0.246. Markets that fail the gate are still visible in the Analytics tab (transparency) but stay off the headline projections list.

Markets are re-evaluated weekly. Removing a market is a normal part of the process. We'd rather ship nothing in a market than ship marginal volume.

Tools shipped inside the workbook

• Bankroll Manager — set bankroll, Kelly fraction, and per-bet cap. Risk-of-ruin is recomputed live.
• Bet Logger — log every wager. The sheet tracks P&L, ROI, CLV per pick, and engine- vs-actual variance.
• Player & Team Deep-Dive — last 5/10/20 game logs so you can sanity-check any projection against recent reality.
• Analytics — engine ROI per market, calibration curves, conviction sparklines, and the gate status of every market we touch.

What we track on ourselves

• ROI per market — flat 1u at -110 across the season backtest. Published in every workbook's Analytics tab.
• Brier score — calibration check independent of W/L luck. Lower is better; 0.25 = pure noise.
• CLV — closing line value. The single best predictor of long-run profitability. Snapped near first pitch, attributed per priced market.

What we don't do

• Tell anyone what to bet.
• Guarantee wins.
• Hide losing streaks or failing markets.
• Ship marginal volume for content's sake.
• Charge before we can prove edge.

Bet responsibly

Edge Equation is a data & analytics service, not financial or gambling advice. Past performance does not predict future results. Models can and will be wrong. Never wager more than you can afford to lose. 21+ where legal. US problem-gambling helpline: 1-800-522-4700.

Try the workbook

Two real .xlsx samples (WNBA + MLB, May 9 2026) are free to download from /samples — no email, no card. Or claim Free May 2026 access on /free-may for a full month of fresh daily workbooks. Post-May pricing lives on /pricing.