Game totals (FT)
Official only when the model states ≥56% — the zone where its hit rate is proven over two backtest seasons. Below that, the read is published as a trend.
AI Trends Journal — MLB
An AI trend is a model signal that doesn't meet every requirement of an official pick: confidence below the validated threshold, unconfirmed pitchers, or a zone still under observation. We publish all of them, frozen at pick time with their stated probability, and settle them against the final score — won or lost. This is our public proving ground: once a zone shows over time that “stated X% = realized X%” at a paying price, it graduates to official.
Why is a trend not an official pick?
First-5 (F5)
Baseball's noisiest market (≈5 runs average, ±3.3 SD): our F5 model is still being stabilized — everything stays a trend for now.
Run line (±1.5)
Official inside the two-season-validated 53-60% confidence zone, with confirmed pitchers and a price that pays the probability. Very high confidences (60%+) are under observation: they win often… at prices that don't always pay.
First inning (NRFI/YRFI)
New engine (July 2026), very well calibrated in backtest — but no zone has yet proven a net profit at real prices across two seasons. Everything is published as a trend, settled nightly, and the zone goes official only if live results confirm.
Live calibration — stated vs realized (last 30 days)
How to read these tables: an honest model must realize what it states — if it says 56%, it should win ~56% of the time. Since June 2026 we have publicly tracked every trend of our historical model — and that tracking showed it stated more than it delivered, the more so the more “confident” it claimed to be (“Historical model” tables, broken down market by market: a model can be right on totals and wrong on the run line). Those lessons fed a progressive overhaul of our models: four seasons of consolidated data, calibration validated over two full backtest seasons. The “New generation” tables track each engine day by day under the same rule — you watch their calibration build live, unfiltered and untouched.
Historical model — Run line
| Stated confidence | Settled trends | Stated (avg) | Realized | Avg odds |
|---|---|---|---|---|
| < 53% | 17 | 48,6% | 76,5% | @ 1,71 |
| 56-60% | 44 | 58,8% | 61,4% | @ 1,67 |
| ≥ 60% | 37 | 65,1% | 70,3% | @ 1,59 |
New generation — Game total
| Stated confidence | Settled trends | Stated (avg) | Realized | Avg odds |
|---|---|---|---|---|
| 53-56% | 19 | 53,5% | 52,6% | @ 1,92 |
New generation — First-5 total
| Stated confidence | Settled trends | Stated (avg) | Realized | Avg odds |
|---|---|---|---|---|
| 53-56% | 23 | 53,5% | 47,8% | @ 1,89 |
New generation — Run line
| Stated confidence | Settled trends | Stated (avg) | Realized | Avg odds |
|---|---|---|---|---|
| 53-56% | 11 | 54,5% | 72,7% | @ 1,89 |
| 56-60% | 23 | 58,1% | 47,8% | @ 1,63 |
| ≥ 60% | 66 | 64,4% | 69,7% | @ 1,66 |
New generation — First inning (NRFI/YRFI)
| Stated confidence | Settled trends | Stated (avg) | Realized | Avg odds |
|---|---|---|---|---|
| 53-56% | 79 | 54,3% | 41,8% | @ 1,86 |
| 56-60% | 61 | 57,4% | 52,5% | @ 1,83 |
| ≥ 60% | 19 | 62,0% | 52,6% | @ 1,74 |
| Date | Game | Market | Trend | Stated prob. | Odds | Result |
|---|---|---|---|---|---|---|
| 02/09 | SEA @ BOS8–3 | IARun line | SEA +1.5 | 58,8% | @ 1,61 | Won |
| 02/09 | PHI @ ARI0–1 | IARun line | ARI +1.5 | 58,8% | @ 1,70 | Won |
| 01/09 | ATL @ WSN5–9 | FTGame total | Under 10.0 | 53,1% | @ 1,88 | Lost |
| 01/09 | SFG @ PIT12–13 | FTGame total | Under 7.5 | 53,3% | @ 1,85 | Lost |
| 01/09 | SFG @ PIT12–13 | RLRun line | SFG +1.5 | 58,3% | @ 1,66 | Won |
| 01/09 | TOR @ CLE1–6 | RLRun line | TOR +1.5 | 62,3% | @ 1,72 | Lost |
| 01/09 | SDP @ CIN3–4 | RLRun line | CIN +1.5 | 64,0% | @ 1,76 | Won |
| 01/09 | ATL @ WSN5–9 | I1First inning (NRFI/YRFI) | Au moins 1 run en 1ʳᵉ manche (YRFI) | 53,6% | @ 1,72 | Lost |
| 01/09 | OAK @ TEX5–8 | I1First inning (NRFI/YRFI) | Aucun run en 1ʳᵉ manche (NRFI) | 53,9% | @ 1,83 | Lost |
| 01/09 | SFG @ PIT12–13 | I1First inning (NRFI/YRFI) | Aucun run en 1ʳᵉ manche (NRFI) | 61,5% | @ 1,64 | Lost |
| 01/09 | STL @ LAD13–8 | I1First inning (NRFI/YRFI) | Au moins 1 run en 1ʳᵉ manche (YRFI) | 57,9% | @ 1,80 | Lost |
| 01/09 | NYY @ LAA7–3 | I1First inning (NRFI/YRFI) | Aucun run en 1ʳᵉ manche (NRFI) | 55,5% | @ 1,71 | Lost |
| 01/09 | MIA @ KCR6–3 | I1First inning (NRFI/YRFI) | Au moins 1 run en 1ʳᵉ manche (YRFI) | 56,4% | @ 1,76 | Lost |
| 01/09 | CHW @ HOU5–1 | I1First inning (NRFI/YRFI) | Aucun run en 1ʳᵉ manche (NRFI) | 55,0% | @ 1,92 | Won |
| 01/09 | BAL @ COL2–4 | I1First inning (NRFI/YRFI) | Au moins 1 run en 1ʳᵉ manche (YRFI) | 54,2% | @ 1,69 | Lost |
| 01/09 | SDP @ CIN3–4 | I1First inning (NRFI/YRFI) | Au moins 1 run en 1ʳᵉ manche (YRFI) | 56,7% | @ 1,80 | Won |
| 01/09 | MIL @ CHC9–4 | I1First inning (NRFI/YRFI) | Au moins 1 run en 1ʳᵉ manche (YRFI) | 56,2% | @ 1,72 | Lost |
| 01/09 | SEA @ BOS9–6 | I1First inning (NRFI/YRFI) | Aucun run en 1ʳᵉ manche (NRFI) | 55,6% | @ 1,71 | Lost |
| 01/09 | PHI @ ARI7–1 | I1First inning (NRFI/YRFI) | Aucun run en 1ʳᵉ manche (NRFI) | 56,2% | @ 1,71 | Lost |
| 01/09 | NYM @ TBR2–6 | F5First-5 total | Under 4.0 | 53,2% | @ 1,95 | Won |
| 01/09 | NYM @ TBR2–6 | RLRun line | NYM +1.5 | 61,3% | @ 1,54 | Lost |
| 01/09 | STL @ LAD13–8 | RLRun line | STL +1.5 | 65,6% | @ 1,80 | Won |
| 01/09 | CHW @ HOU5–1 | RLRun line | HOU +1.5 | 65,0% | @ 1,62 | Lost |
| 01/09 | SEA @ BOS9–6 | RLRun line | SEA +1.5 | 60,8% | @ 1,49 | Won |
| 01/09 | PHI @ ARI7–1 | RLRun line | ARI +1.5 | 64,4% | @ 1,68 | Lost |
| 01/09 | NYM @ TBR2–6 | I1First inning (NRFI/YRFI) | Aucun run en 1ʳᵉ manche (NRFI) | 53,5% | @ 1,88 | Lost |
| 01/09 | TOR @ CLE1–6 | I1First inning (NRFI/YRFI) | Aucun run en 1ʳᵉ manche (NRFI) | 60,2% | @ 1,72 | Won |
| 01/09 | NYM @ TBR2–6 | IARun line | NYM +1.5 | 63,4% | @ 1,55 | Lost |
| 01/09 | SFG @ PIT12–13 | IARun line | SFG +1.5 | 61,9% | @ 1,68 | Won |
| 01/09 | STL @ LAD13–8 | IARun line | STL +1.5 | 58,8% | @ 1,80 | Won |
| 01/09 | CHW @ HOU5–1 | IARun line | CHW +1.5 | 70,7% | @ 1,44 | Won |
| 01/09 | TOR @ CLE1–6 | IARun line | TOR +1.5 | 58,8% | @ 1,71 | Lost |
| 01/09 | SDP @ CIN3–4 | IARun line | CIN +1.5 | 52,6% | @ 1,75 | Won |
| 01/09 | MIL @ CHC9–4 | IARun line | MIL +1.5 | 64,0% | @ 1,55 | Won |
| 01/09 | SEA @ BOS9–6 | IARun line | SEA +1.5 | 73,5% | @ 1,48 | Won |
| 01/09 | PHI @ ARI7–1 | IARun line | ARI +1.5 | 58,8% | @ 1,65 | Lost |
| 31/08 | SDP @ CIN5–0 | I1First inning (NRFI/YRFI) | Au moins 1 run en 1ʳᵉ manche (YRFI) | 55,9% | @ 1,92 | Lost |
| 31/08 | MIL @ CHC3–17 | I1First inning (NRFI/YRFI) | Aucun run en 1ʳᵉ manche (NRFI) | 54,1% | @ 1,99 | Lost |
| 31/08 | NYM @ TBR3–2 | FTGame total | Under 8.0 | 53,6% | @ 1,98 | Won |
| 31/08 | BAL @ COL2–1 | FTGame total | Under 11.0 | 54,2% | @ 1,87 | Won |
Frequently asked questions
What is the “stated probability”?
The calibrated probability the model gave its trend at pick time. Our transparency commitment: over time, a zone stated at 56% must win ~56% of the time — this page lets you verify it.
Why publish losing trends?
Because a complete record is the only honest one. Every trend is frozen at pick time and settled against the final score, no filtering.
When does a trend become an official pick?
When its confidence zone has proven — in a two-season backtest AND live — that the stated rate is realized at a price that pays it. Official MLB picks follow those validated zones.
