16 of 132 pitchers with a real velocity change, 8 of 408 more whose stuff or command has moved, 8 of 140 hitters with a measurable skill shift.
The inputs, not the results. A pitcher who has lost velocity is a different pitcher before his ERA catches up, and a hitter whose contact quality has shifted is a different hitter before his batting average agrees.
Year-over-year on the primary fastball, for pitchers with at least 100 of them in both seasons. Velocity is the earliest and least ambiguous signal an arm gives you: it moves for physical reasons and it stabilises faster than any result stat. A full mile per hour is roughly the tenth percentile of the league, real, not drift.
| Pitcher | Pos | Pitch | 2025 | 2026 | Change | Whiff% | Our rank |
|---|---|---|---|---|---|---|---|
| John King | RP | SI | 93.0 | 90.4 | -2.6 mph | 15.8 | #501 |
| Lucas Giolito | SP | FF | 93.3 | 90.8 | -2.5 mph | 16.7 | #1347 |
| Jeremiah Estrada | RP | FF | 97.9 | 95.8 | -2.1 mph | 28.0 | #745 |
| Bailey Ober | SP | FF | 90.3 | 88.2 | -2.1 mph | 15.1 | #303 |
| Luis García | RP | SI | 96.9 | 95.0 | -1.9 mph | 9.4 | #752 |
| Bryan Abreu | RP | FF | 97.3 | 95.4 | -1.9 mph | 26.7 | #460 |
| Kirby Yates | RP | FF | 92.8 | 90.9 | -1.9 mph | 28.8 | #663 |
| Reid Detmers | SP+RP | FF | 95.8 | 94.1 | -1.7 mph | 22.0 | #76 |
The same measure the other way. Added velocity on a starter often means a mechanical change or a role change; on a reliever it is usually the shorter outings doing the work.
| Pitcher | Pos | Pitch | 2025 | 2026 | Change | Whiff% | Our rank |
|---|---|---|---|---|---|---|---|
| Kyle Hart | RP | SI | 91.4 | 93.8 | +2.4 mph | 12.2 | #632 |
| Antonio Senzatela | RP | FF | 95.0 | 97.3 | +2.3 mph | 29.5 | #459 |
| Chris Murphy | RP | FF | 94.3 | 96.3 | +2.0 mph | 28.2 | #818 |
| Camilo Doval | RP | SI | 96.6 | 98.5 | +1.9 mph | 17.8 | #686 |
| Yoendrys Gómez | SP+RP | FF | 93.8 | 95.7 | +1.9 mph | 25.1 | #275 |
| Roki Sasaki | SP | FF | 96.1 | 97.9 | +1.8 mph | 20.4 | #366 |
| Ryan Yarbrough | RP | FC | 83.2 | 85.0 | +1.8 mph | 18.6 | #658 |
| Adrian Morejon | RP | SI | 97.7 | 99.5 | +1.8 mph | 19.6 | #320 |
Stuff+, Location+ and Pitching+ measure the pitch itself rather than what the hitter did with it, so they move before the ERA and before the strikeout rate. This is a slower read than velocity and a broader one: it catches a new slider or a command gain that the radar gun never sees. Ordered by the size of the change, then by where the arm sits on our board.
| Player | Pos | Change | What moved | Score | Our rank |
|---|---|---|---|---|---|
| Emerson Hancock | SP+RP | Transformational Change | Stuff+ +10; Pitching+ +13; Whiff% +3.9 | 100 | #139 |
| Griffin Jax | SP+RP | Transformational Change | Stuff+ −12; Whiff% −6.3; Pitching+ −12 | 100 | #364 |
| Roki Sasaki | SP | Transformational Change | New pitch: SL +21; FF velocity (mph) +1.8; Stuff+ +20 | 100 | #366 |
| Didier Fuentes | SP+RP | Transformational Change | New pitch: SL +23; FF velocity (mph) +1.2; Pitching+ +15 | 100 | #431 |
| Reynaldo López | SP+RP | Transformational Change | New pitch: SL +31; FF velocity (mph) −1.4; Whiff% +19 | 100 | #442 |
| Antonio Senzatela | RP | Transformational Change | FF velocity (mph) +2.3; Stuff+ +17; Pitching+ +14 | 100 | #459 |
| Ryan Rolison | RP | Transformational Change | FF velocity (mph) +1.7; New pitch: ST +14; Pitching+ +12 | 100 | #477 |
| Chase Petty | RP | Transformational Change | New pitch: CH +23; New pitch: ST +18; Whiff% −14 | 100 | #979 |
Contact quality and swing decisions, the parts of a hitting line that settle before the results do.
| Player | Pos | Change | What moved | Score | Our rank |
|---|---|---|---|---|---|
| Jordan Walker | OF | Major Change | xwOBA +0.079; xSLG +0.128; xBA +0.070 | 63 | #52 |
| Cal Raleigh | C/DH | Major Change | xwOBA −0.076; xSLG −0.174; xBA −0.052 | 63 | #210 |
| JJ Bleday | OF | Major Change | xwOBA +0.083; xSLG +0.108; xBA +0.052 | 63 | #198 |
| George Springer | DH/OF | Major Change | xwOBA −0.097; xSLG −0.194; xBA −0.061 | 63 | #173 |
| Ezequiel Tovar | SS | Major Change | xwOBA −0.048; xSLG −0.086; xBA −0.043 | 63 | #415 |
| Brandon Nimmo | OF | Major Change | xwOBA +0.051; xSLG +0.085; xBA +0.040 | 63 | #170 |
| Corey Seager | SS | Major Change | xwOBA −0.066; xSLG −0.122; xBA −0.056 | 63 | #189 |
| Salvador Perez | DH/C/1B | Major Change | xwOBA −0.060; xSLG −0.125; xBA −0.040 | 63 | #187 |
Velocity is the most trustworthy line here. It stabilises quickly, it moves for physical reasons, and a starter who has genuinely lost a mile per hour is usually telling you something before the ERA does. It is measured on the primary fastball only, and only for arms with a real sample in both seasons.
The stuff and command section is a descriptive layer and is not part of our projection, and neither is the hitter section. Neither has been validated into the rankings and we do not pretend otherwise: where these and the board disagree, that is something to watch rather than a correction to either.
Low-confidence signals are excluded from both sections, a little under half the feed. A small reading off a handful of batted balls or a few dozen pitches is noise wearing a decimal point.
Curated picks where the model has the highest decision conviction. Updated every render.
Run rankings to populate Market Edge.
Run rankings first.
Mark a player as drafted to get a recommendation.
Studies and awards - the research-side surfaces of the managr platform.
Live snapshot of the projection system.
Backtest, parsimony, ablation, and benchmark - one synthesized report. Output renders in Validation.
Final Value = Raw Projection × MasterConfidence × TeamContext. Each layer answers one question - no overlap.
Recency weighting: prior seasons contribute by recency (more recent = more weight) and sample size (more PA = more weight).
Shrinkage: observed rates regress toward position-specific population means by an amount inversely proportional to sample size. Catches small-sample outliers.
Quality-of-contact adjustments: xwOBA, barrel rate, and bat-tracking metrics replace luck-driven outcome stats with skill-driven ones.
PT modeling: projected PA is anchored to workload tier (full-time, regular, platoon, backup catcher) using historical role distributions.
Monte Carlo: N simulated seasons per player using projected mean + uncertainty, producing P10 / P50 / P90 distribution and bust%.
Confidence layers: four orthogonal multipliers: Roster (depth chart), Role (PT certainty), Sample (career PA), Market (consensus alignment). The Audit tab shows all four for every player.
VAR: Value Above Replacement at the player's primary position. Replacement levels are floored per position so SS scarcity doesn't artificially inflate stable middle infielders.
Tune component weights against historical seasons. Stored in session.
-
-
-
Walk-forward backtests, calibration quality, and benchmark comparisons. Run walk-forward first - most tools depend on its pair pool.
Projects every historical batter-season from prior data only. Reports RMSE, MAE, Spearman ρ, hit rates. Populates the pair pool other validators use.
Walk-forward over historical seasons. Reports RMSE, MAE, Spearman ρ, top-N hit rates.
Distribution, uncertainty, per-archetype performance, calibrated tiers, draft sim.
Load any rival projection or ADP source. Auto-detects player_name + rank / adp / projected.
Where the model finds value the market is missing.
Curated picks from current rankings.
Where the model has measurable advantage.
The safety layer. Realism, false-confidence, forensics - what to remove.
The most important governance tools. Output renders in Validation.
Per-era ablation, error clusters, bias, correlations, removals. Each tells you what to remove. Run walk-forward first.
The smallest model that retains predictive power. Every feature beats the burden of proof.
Live pipeline status and data freshness.
-
Last known status of each underlying data source.
Source status will appear once data has been refreshed.
Issues from the most recent data refresh, if any.
-
MVP, Cy Young, Rookie of the Year - historical winners with their stats, plus model-predicted current-season winners.
Predictions from the current 2026 projection model. Top candidates per award based on projected fantasy points + advanced-stat underlying. League assignment from current team.
Coaching rosters for every MLB team plus a multi-year Fantasy Points Above Average ranking of every MLB coach.
Findings article + all-time top-100 performer leaderboard from every World Baseball Classic (2006-2026).
A growing collection of fantasy baseball studies. Each card opens a detail page with the methodology, the data sources, and (where the data exists today) live computed findings.
Active player injuries, refreshed from upstream sources.
| Player | Team | Pos | Status | Explanation | Replacement |
|---|
Enter players for each side, one per line. Values use your scoring weights and injury-adjusted projections.
| Player | Pos | ProjPts | Status |
|---|
| Player | Pos | ProjPts | Status |
|---|
Every signal, formula, and data source the model uses for player evaluation - organized by product.
Configure your draft session. This stays on this device only.