Building the record in public, since 2026-05-22. Every pick we make is published — wins and losses, including days our own Kelly bet/pass gate says "no edge." Most pick services hide their losses; we publish ours. The longer the sample grows, the more the numbers mean. Use it accordingly. Not financial advice. For entertainment only.

How the Model Works

One MLB pick a day. Built on the same kinds of inputs bookmakers weigh — projected runs, line movement, situational context — and made public so you can see every win and every loss.

Strongest Play Record
ATS %
Moneyline ATS
Totals ATS
Record since

The Method, in Plain English

1

Project every batter's runs from xwOBA

For each starting batter we take a 3-year weighted xwOBA baseline (current season 45%, prior 35%, two years ago 20%) and run it through a Pythagorean run-expectancy model. That's how many runs the lineup should produce against an average pitcher in an average park.

2

Adjust for everything the bookmakers also adjust for

Opposing starter quality (xERA tier + velocity trend) and handedness splits. Bullpen availability scaled by expected inning share. Park run factor. Game-time weather (wind direction + speed, temperature). 14-day form. Schedule strength.

3

Compare model output to the closing Vegas line

For every game we compute three numbers: moneyline edge (percentage points), runline edge (runs vs the spread), and total edge (runs vs O/U). Anything inside ±1pp / ±0.5 runs we treat as noise.

4

Stack 50+ situational trends on top

Pitcher third time through the lineup. Wind blowing out 12+ mph. Team coming off a shutout. Bullpen depleted from yesterday's blowout. Each trend is back-tested against 32,000+ historical games (Princeton + SBR + OddsPortal databases, 2010-2025) and only counted if the sample is large enough to be real signal.

5

Pick ONE play per day — the highest composite score

Composite = 35% projection edge + 25% confidence + 25% situational alignment + 15% edge size. Then a Kelly bet/pass gate filters out picks that look real but don't clear minimum confidence + edge thresholds.

6

Settle every pick the next morning

At 9 AM ET we pull actual game results from MLB Stats API, settle yesterday's pick (win / loss / push), and update the public record. No quietly deleting losses. No "we were 50-0 in May" charts.

What you see vs what we see

Free users get the daily pick + the running record. Paid tiers unlock the full Betting Analysis grid (every game's ML/RL/Total leans with edge and confidence), Game Deep Dives with pitcher matchups and lineup projections, and a Pick Tracker with personal P&L. Everything is the same engine output — we don't have "premium picks" we're hiding from free users. The free tier shows you the strongest play; paid tiers show you the full board.

Why one pick a day, not ten

Most pick services flood you with plays because volume hides the losses — if you "won 6 of 10," nobody notices the 4 losses. We post one play because that's what the model is actually highest-confidence on. If today's board is weak, the Kelly gate says PASS and we don't tweet a pick. That happens. It's the honest version.

See today's pick + full breakdown

Live dashboard with the day's strongest play, supporting trends, and the running record — free.

Open the dashboard

For entertainment purposes only. Not financial or betting advice.