KSplitAnalytics
Model Diagnostics — Live Season Log
Games Logged 3372
Updates in real time
Total Games Logged
3372
season to date
MAE (Ks)
1.755
median absolute error
Avg Signed Error
0.013
direction of bias
Within ±1K Rate
50.52%
within ±2K: 74.61%
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 = 1650 games
2+ Ks Over Line
15.45%
Actual Ks Over the Line
44.48%
2+ Ks Under Line
36.79%
Mid | Tail-Supported
n = 1295 games
2+ Ks Over Line
21.08%
Actual Ks Over the Line
51.43%
2+ Ks Under Line
31.97%
High | Tail-Driven
n = 426 games
2+ Ks Over Line
20.89%
Actual Ks Over the Line
54.23%
2+ Ks Under Line
31.92%
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) bucketHitsnHit %
<30%337119428.22%
30–39.99%412126732.52%
40–49.99%25173834.01%
50–59.99%5314636.30%
60–69.99%62326.09%
70%+020.00%
Total Games3370
03 — Tail Environment
Strikeout Environment Classification
Environment type tracks the structural conditions around each game's K distribution.
Environment TypeSample SizeActual Ks: 2+ Ks Over the LineActual Ks Exactly 1 Over LineActual Ks Exactly 1 Under LineActual Ks: 2+ Ks Under the Line
Fragile Tail Environment156715.06%12.83%19.21%36.38%
Low Tail Environment7924.05%7.59%20.25%31.65%
Balanced Tail Environment87220.64%13.99%17.78%29.70%
Balanced Tail (Accessible)42721.31%12.88%17.80%33.26%
Tail-Friendly Environment25719.07%13.62%13.62%34.24%
Stable Tail Environment16924.85%13.61%17.16%26.04%
All Environments3371
04 — Median by Tier
Exact Hits by Pitcher Tier
Exact hits become less frequent as distributions widen in higher strikeout tiers.
Elite
n = 417 games
MAE
1.949
Median Exact Hit
17.56%
Within ±1
44.36%
Within ±2
68.87%
Mid
n = 991 games
MAE
1.861
Median Exact Hit
17.62%
Within ±1
48.09%
Within ±2
70.11%
Low
n = 1992 games
MAE
1.661
Median Exact Hit
18.00%
Within ±1
52.96%
Within ±2
77.97%
05 — Median Diagnostics & Edge Band
Error Distribution & ROI by Edge Bucket
Error BucketsMedian
-2K (From Actual)12.4%
-1K17.5%
Exact Hit17.7%
+1K14.5%
+2K11.3%
Big Miss % ABS Err>2.5)25.4%
Edge Band (Best Edge)Sample SizeROI (Units / Bet)
< 0%00.00
0–4.99%13630.02
5–9.99%10730.01
10–14.99%5940.02
15–19.99%229-0.06
20–24.99%79-0.14
25–29.99%30-0.02
30%+4-0.09
06 — Over/Under Edge Band Performance
ROI & Unit P/L by Edge Band Bucket
Overs
Edge Band (Overs)Sample SizeROI (Units / Bet)Unit P/L
0–4.99%7000.00-1.66
5–9.99%597-0.03-18.25
10–14.99%3300.026.80
15–19.99%119-0.07-8.32
20–24.99%39-0.18-7.03
25–29.99%12-0.20-2.39
30%+3-0.46-1.38
Total1800-0.02-32.23
Unders
Edge Band (Unders)Sample SizeROI (Units / Bet)Unit P/L
0–4.99%6620.0534.55
5–9.99%4760.0525.29
10–14.99%2640.012.84
15–19.99%110-0.06-6.29
20–24.99%40-0.09-3.74
25–29.99%180.091.66
30%+11.021.02
Total15710.0455.33
07 — Rolling Window Summary
Combined P/L Across Edge Bands
L200 All
Edge BandUnit P/L
0–4.99%-9.10
5–9.99%-4.55
10–14.99%-7.27
15–19.99%-3.55
20–24.99%0.00
25–29.99%0.00
30%+0
L200 Total-24.47
L50 All
Edge BandUnit P/L
0–4.99%-12.64
5–9.99%-8.37
10–14.99%-7.59
15–19.99%-1.31
20–24.99%0.00
25–29.99%0
30%+0
L50 Total-29.92
KSplitAnalytics.com
Live season log · Updates as games are recorded

Today's Board · Pitcher Distributions