KSplitAnalytics
Model Diagnostics — Live Season Log
Games Logged 942
Updates in real time
Total Games Logged
942
season to date
MAE (Ks)
1.761
median absolute error
Avg Signed Error
-0.165
direction of bias
Within ±1K Rate
49.47%
within ±2K: 75.27%
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 = 417 games
2+ Ks Over Line
16.31%
Actual Ks Over the Line
43.65%
2+ Ks Under Line
37.17%
Mid | Tail-Supported
n = 409 games
2+ Ks Over Line
19.80%
Actual Ks Over the Line
50.86%
2+ Ks Under Line
30.07%
High | Tail-Driven
n = 114 games
2+ Ks Over Line
21.93%
Actual Ks Over the Line
53.51%
2+ Ks Under Line
33.33%
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%6621530.70%
30–39.99%11839729.72%
40–49.99%7323830.67%
50–59.99%237132.39%
60–69.99%41723.53%
70%+020.00%
Total Games940
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 Environment33514.33%13.43%17.91%39.40%
Low Tail Environment7924.05%7.59%20.25%31.65%
Balanced Tail Environment26721.35%11.24%19.85%27.34%
Balanced Tail (Accessible)14316.08%11.89%19.58%34.27%
Tail-Friendly Environment5922.03%6.78%15.25%35.59%
Stable Tail Environment5824.14%13.79%13.79%27.59%
All Environments941
04 — Median by Tier
Exact Hits by Pitcher Tier
Exact hits become less frequent as distributions widen in higher strikeout tiers.
Elite
n = 140 games
MAE
1.964
Median Exact Hit
16.79%
Within ±1
43.80%
Within ±2
70.80%
Mid
n = 227 games
MAE
1.739
Median Exact Hit
19.82%
Within ±1
49.55%
Within ±2
74.76%
Low
n = 577 games
MAE
1.715
Median Exact Hit
17.05%
Within ±1
50.97%
Within ±2
76.85%
05 — Median Diagnostics & Edge Band
Error Distribution & ROI by Edge Bucket
Error BucketsMedian
-2K (From Actual)15.3%
-1K18.3%
Exact Hit17.6%
+1K13.6%
+2K10.5%
Big Miss % ABS Err>2.5)24.6%
Edge Band (Best Edge)Sample SizeROI (Units / Bet)
< 0%00.00
0–4.99%3810.00
5–9.99%2850.00
10–14.99%149-0.01
15–19.99%77-0.02
20–24.99%30-0.34
25–29.99%12-0.20
30%+40.03
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%219-0.044-9.68
5–9.99%189-0.054-10.23
10–14.99%118-0.015-1.75
15–19.99%640.0080.49
20–24.99%24-0.393-9.42
25–29.99%11-0.130-1.43
30%+3-0.307-0.92
Total628-0.0525-32.94
Unders
Edge Band (Unders)Sample SizeROI (Units / Bet)Unit P/L
0–4.99%1620.06911.16
5–9.99%960.10610.19
10–14.99%310.0190.58
15–19.99%13-0.172-2.24
20–24.99%6-0.140-0.84
25–29.99%1-1.020-1.02
30%+11.0201.02
Total3100.060818.85
07 — Rolling Window Summary
Combined P/L Across Edge Bands
L200 All
Edge BandUnit P/L
0–4.99%4.04
5–9.99%-1.52
10–14.99%7.21
15–19.99%1.64
20–24.99%-1.75
25–29.99%0
30%+0
L200 Total9.62
L50 All
Edge BandUnit P/L
0–4.99%9.06
5–9.99%-3.98
10–14.99%6.85
15–19.99%2
20–24.99%-0.51
25–29.99%0
30%+0
L50 Total13.42
KSplitAnalytics.com
Live season log · Updates as games are recorded

Today's Board · Pitcher Distributions