KSplitAnalytics
Model Diagnostics — Live Season Log
Games Logged 2
Updates in real time
Total Games Logged
2
season to date
MAE (Ks)
0.500
median absolute error
Avg Signed Error
0.500
direction of bias
Within ±1K Rate
100.00%
within ±2K: 100.00%
01 — Ceiling Profile
How Do Ceiling Profile Labels Perform?
Tracks how often each ceiling profile delivers upside signal. High | Tail-Driven games show the highest 2+ over rates as the log grows — this table confirms or challenges that signal in real time.
Low | Centered
n = 1 games
2+ Ks Over Line
0.00%
Within ±1 Strikeout of Line
100.00%
2+ Ks Under Line
0.00%
Mid | Tail-Supported
n = —
2+ Ks Over Line
—
Within ±1 Strikeout of Line
—
2+ Ks Under Line
—
High | Tail-Driven
n = —
2+ Ks Over Line
—
Within ±1 Strikeout of Line
—
2+ Ks Under Line
—
02 — Right Tail Calibration
Mean-Based Right Tail Tables
When the model assigns a given upside probability, how often does it actually happen? O/E near 1.00 means the model is well-calibrated at that bucket. Values above 1.0 mean reality exceeds the model's prediction — below 1.0 means the model is over-calling it.
| +1 tail calibration (bucketed by P(+1)) | ||||
|---|---|---|---|---|
| P(+1) bucket | Hits | n | Hit % | |
| <30% | 0 | 1 | 0.00% | |
| 30–39.99% | 0 | 1 | 0.00% | |
| 40–49.99% | 0 | 0 | ||
| 50–59.99% | 0 | 0 | ||
| 60–69.99% | 0 | 0 | ||
| 70%+ | 0 | 0 | ||
| Total Games | 2 |
03 — Tail Environment
Strikeout Environment Classification
Environment type tracks the structural conditions around each game's K distribution.
| Environment Type | Sample Size | Actual Ks: 2+ Ks Over the Line | Actual Ks Exactly 1 Over Line | Actual Ks Exactly 1 Under Line | Actual Ks: 2+ Ks Under the Line | |||
|---|---|---|---|---|---|---|---|---|
| Fragile Tail Environment | 2 | 0 | 0 | 1 | 0 | |||
| Low Tail Environment | 0 | |||||||
| Balanced Tail Environment | 0 | |||||||
| Balanced Tail (Accessible) | 0 | |||||||
| Tail-Friendly Environment | 0 | |||||||
| Stable Tail Environment | 0 | |||||||
| All Environments | 2 |
04 — Median by Tier
Exact Hits by Pitcher Tier
Exact hits become less frequent as distributions widen in higher strikeout tiers.
Elite
n = 0 games
MAE
—
Median Exact Hit
—
Within ±1
—
Within ±2
—
Mid
n = 1 games
MAE
0.025
Median Exact Hit
100.00%
Within ±1
100.00%
Within ±2
100.00%
Low
n = 1 games
MAE
0.067
Median Exact Hit
0.00%
Within ±1
100.00%
Within ±2
100.00%
05 — Median Diagnostics & Edge Band
Error Distribution & ROI by Edge Bucket
| Error Buckets | Median | |||||||
|---|---|---|---|---|---|---|---|---|
| -2K (From Actual) | 0.0% | |||||||
| -1K | 0.0% | |||||||
| Exact Hit | 50.0% | |||||||
| +1K | 50.0% | |||||||
| +2K | 0.0% | |||||||
| Big Miss % ABS Err>2.5) | 0.0% |
| Edge Band (Best Edge) | Sample Size | ROI (Units / Bet) | ||||||
|---|---|---|---|---|---|---|---|---|
| < 0% | 0 | 0.00 | ||||||
| 0–4.99% | 1 | -1.00 | ||||||
| 5–9.99% | 0 | 0.00 | ||||||
| 10–14.99% | 1 | -1.00 | ||||||
| 15–19.99% | 0 | 0.00 | ||||||
| 20–24.99% | 0 | 0.00 | ||||||
| 25–29.99% | 0 | 0.00 | ||||||
| 30%+ | 0 | 0.00 |