11 players moved more than 100 projected points in the last day.
The board re-ran and 11 players moved by more than 100 projected points in the last day. That is roughly the top 1% of daily movement, on a normal day the median player shifts under 3 points, so these are the re-forecasts worth knowing about, not noise.
| Player | Pos | Change | Proj pts now | Value | Why |
|---|---|---|---|---|---|
| Riley Greene | OF/DH | +111 | 462 | +58 | Re-forecast |
| Player | Pos | Change | Proj pts now | Value | Why |
|---|---|---|---|---|---|
| James Wood | OF/DH | -224 | 294 | -231 | Health |
| Ryan Helsley | RP | -147 | 89 | -31 | Health |
| Corbin Burnes | SP | -135 | 86 | -62 | Health |
| Byron Buxton | OF/DH | -135 | 236 | -209 | Health |
| Cole Ragans | SP | -124 | 189 | -43 | Health |
| Nick Kurtz | 1B | -119 | 285 | -179 | Health |
| Brandon Woodruff | SP | -111 | 262 | -110 | Health |
| Spencer Strider | SP | -107 | 103 | -45 | Health |
| Robert Garcia | RP | -103 | 90 | -16 | Health |
| Ben Rice | 1B/DH/C | -102 | 385 | -41 | Re-forecast |
2 of these 11 moved with no injury designation attached. That is the engine re-forecasting a healthy player, a role change, a call-up sticking, playing time being reallocated, and it is the more actionable half of this list, because nobody else is watching for it: Riley Greene (+111), Ben Rice (-102).
Riley Greene is the only name on this list that moved up without an injury flag doing the work, and that makes him the one case here that should actually change a roster. A jump of 111 projected points to 462 is not a rounding adjustment. It is the model rewriting what it thinks his rest-of-season rate looks like, on a healthy player, with no games-played mechanism to hide behind. The value move of plus 58 is smaller than the points move, which is what you would expect: outfield is deep enough that raw counting stats do not convert one for one into scarcity. Still, the direction is unambiguous and it is the only unambiguous upward signal in the window.
The case against buying it is the length of the window. A re-forecast on a healthy hitter over a stretch this short is usually built on a hot run of contact, and the model cannot tell you whether the barrels are real or the schedule was soft. If you want the falsifier, it is simple: watch whether the underlying rate holds when the next re-forecast lands. If Greene gives back forty or fifty of those points on the next pass with no injury attached, the engine was chasing a stretch of at-bats and you paid for noise. If the 462 holds or nudges higher, he is being priced as a top-of-the-board outfielder and the plus 58 was too conservative. I would trade for him now and accept the risk. The cost of being wrong is that you gave up a mid-tier arm for a good outfielder instead of a great one.
Ben Rice is the interesting negative, because he is the other re-forecast and the numbers pull in opposite directions. Down 102 projected points to 385, but only minus 41 in value. That gap is the whole story. Rice carries first base, DH and catcher eligibility, and catcher is where value comes from having nobody behind you. So the model can shave a hundred points off his line and the market barely flinches, because the alternative at the position is worse than the alternative in the outfield. Do not sell into this. A 385-point projection with catcher eligibility is still a starting asset in almost any format, and the value column is telling you the league already knows it.
The health moves are a different animal and mostly do not require action. James Wood at minus 224 points and minus 231 in value is the largest single drop on the board, and the two numbers moving together is the signal: the games are simply gone, and there is no positional cushion to absorb them. That is not the model changing its mind about Wood the hitter. It is arithmetic on a shortened denominator, already reflected in whatever you would get for him.
The pitchers are where the mechanical drops read cheapest. Corbin Burnes loses 135 projected points down to 86, but only 62 in value, and Spencer Strider loses 107 to 103 with a value hit of 45. Both ratios say the same thing: replacement-level starting pitching is close enough that missing time costs you far less than the point total suggests. If you have the IL spot, these are the roster decisions that make themselves. Hold, stash, and let the projection catch back up if the designation lifts. The one genuine cost is opportunity: an IL slot occupied by an arm projected for 86 points is a slot not holding a healthy bat, and if the designation drags into September that stash was dead weight.
These are projection changes, not results. A jump usually means the engine now expects more playing time, a return from the IL, a rotation or bullpen role changing, a call-up sticking, and a drop usually means the opposite. The Note column flags anyone currently carrying an injury designation, which explains a large share of both directions.
Proj pts is the full-season projection as it stands today and Value is the replacement-adjusted number the boards sort on. Generated from the daily board archive, which is why the window is exact rather than "recently".
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.