Call-Up Probability Engine  ·  First Results In  ·  June 18, 2026

Who Gets
Called Up
Next.

One question: when does this player get called up? The question is timing, and timing is measurable. 28 prospects scored using 12 quantifiable features, 30 org coefficients, and a 3-pathway call-up date engine.

See the Leaderboard How it works
One email a week. Free. Unsubscribe anytime.
MKDC Baseball
14/14
Called Correctly
28
Players Scored
100%
Ranked In Order
90d
Forecast Window
3
Misses Logged
Run: March 20, 2026 · Resolved: June 18, 2026 · Model v0.4
Results are in. The first cohort resolved June 18. Fourteen of 28 reached the majors and the model ranked all 28 in the right order. See the full breakdown ›
New batch. Sub-Batch B is live, 14 prospects scored on the recalibrated v0.5 engine. Thomas White leads at 62 percent. Window closes September 9 ›
Resolved · June 18, 2026 · Sub-Batch A
First Cohort Results
Full calibration log
28
Prospects scored
14
Reached the majors
0.269
Raw Brier score
0.142
Corrected on v0.5

Every March 20 prediction resolved on June 18 and is logged in public. The model ranked all 28 in the right order. See the full breakdown.

Live Board · Sub-Batch B · Model v0.5 · Window closes September 9
CUP Leaderboard
Sub-Batch A resolved June 18. 14 of 28 reached the majors and the model ranked all 28 in the right order. See the calibration log.
View Sub-Batch B
Model v0.4 · Sub-Batch A · Public Track Record
Calibration Checkpoints
Full log
April 9, 2026
PPI Deadline
PPI window closes. Downgrade any PPI-High player not on an MLB roster. Flags: Emerson, Clark, White.
01
May 1, 2026
Week 6 - Svc Time
First service time windows unlock. Players to reassess: Miller, Benge, Basallo, Veen, Messick, Williams.
02
May 29, 2026
Week 10
Majority of service time windows resolved. Reassess Condon and remaining Pathway A predictions.
03
June 18, 2026 · Complete
90-Day Resolution
Done. The model called 14 of 14 and ranked all 28 players in order. See the full results and what changes next.
✓
Free signup · Instant download

Know Before
It Happens.

Subscribe and get the Org Coefficient Cheat Sheet: all 30 MLB teams ranked by how aggressively they promote prospects, the single biggest factor in call-up timing. Then every week you get what changed: injuries, roster moves, PPI deadlines, and CUP revisions.

14 of 28 called correctly in the first cohort. 0.142 Brier score. Every prediction is graded in public.
You get, free:
  • The Org Coefficient Cheat Sheet, all 30 teams ranked (instant)
  • Weekly CUP updates on every open prospect
  • PPI deadline tracking and formal downgrade notices
  • Calibration notes whenever the model revises a probability
  • First word when a new sub-batch runs
No spam. Unsubscribe anytime. Outputs are model-generated probabilities, not picks.

MLB Prospect Call-Up Predictions: How the Model Works

Most prospect coverage focuses on who a player is. Very little answers when they arrive. MKDC Baseball is built around a single question: when will an MLB prospect get called up, and why?

The Call-Up Probability Engine evaluates every tracked prospect across 12 quantifiable features: level proximity, age relative to league, 30-day performance, 40-man roster status, organizational promotion history, positional scarcity, service time considerations, and more. These inputs generate a CUP score (Call-Up Probability within 90 days) and an ECD (Estimated Call-Up Date) via one of three structured pathways.

Why timing is predictable

MLB promotions are not random. Service time mechanics create calendar-driven windows. Organizational behavior is quantifiable. Injuries create immediate openings. The model integrates all three to estimate timing, not just readiness.

What makes this different

Every output is logged publicly before outcomes are known. The June 18, 2026 calibration checkpoint is a hard public test. No retroactive adjustments. The model is scored on a Brier score against binary outcomes.

Prospect analysis → How the model works → Baseball metrics explained → How orgs handle prospects →
Four-Stage Pipeline · Model v0.4
How the Engine Works
Full methodology
01
⚙️
12 Feature Inputs
Level proximity, age vs. league avg, 30-day performance stats, 40-man status, org opportunity, options remaining, position scarcity, performance trend, spring signal, prospect tier, and Rule 5 flag. All sourced from public data at evaluation date.
Stage 1–2
02
📊
CUS Score 0–100
All feature scores are summed and normalized to a 0–100 Composite Upward Score. No post-hoc weighting. Weights are baked into defined scoring ranges. Immutable at run date.
Stage 3
03
🎯
CUP Probability
CUS converts to a Call-Up Probability (CUP), then three multipliers are applied in sequence: org promotion behavior, positional base rate, and service time suppression. CUP is the final number you see in the leaderboard.
Stage 3
04
📅
ECD Engine
CUP converts to an Estimated Call-Up Date (ECD) through one of three pathways: service time windows (tight range), opportunity or injury (medium range), or performance trajectory (wide range). Each pathway carries a confidence tier.
Stage 4 · v0.4