Prediction Accuracy: November 2026
Every Best Pick and Value Analysis of the month, graded against the final result. Hits and misses count alike; void matches are left out.
Month to date, graded up to 4 Nov 2026. Final from the 2nd of next month.
Hit rate in November 2026
Best Picks
The single highest-conviction selection per fixture, across all markets.
+5.0 pts vs October 2026
Value Analysis
Selections where the model's probability diverges most from consensus market pricing.
-0.9 pts vs October 2026
Compared to guessing
An accuracy figure means nothing on its own. The only useful question is what a naive rule would have scored on exactly the same matches.
Measured across every graded fixture, not a selected subset. Home advantage is why the naive rule scores as well as it does; the gap above it is what the model contributes. n = 1,015.
Day by day in November 2026
Each line is a seven-day rolling average of settled selections, with a node marking the days behind it. Days with nothing settled break the line rather than being bridged across.
| Date | Best Picks | Value Analysis |
|---|---|---|
| 01.11.2026 | 76.2% | 67.2% |
| 02.11.2026 | 76.7% | 67.0% |
| 03.11.2026 | 77.0% | 66.4% |
| 04.11.2026 | 77.0% | 65.1% |
Are the probabilities honest?
This is the test that matters. We group every match-result forecast by the probability we published, then plot what actually happened. A calibrated model sits on the diagonal.
What this chart coversMatch result across every graded fixture, not just selected picks - a selected subset could not test calibration honestly. Buckets holding too few fixtures to plot are merged into the end points, and point size scales with sample. Vertical bars are 95% intervals: a thin bucket is an uncertain reading, not a precise miss.
117 fixtures sat in bands holding fewer than 50 each and are not plotted.
Brier score: 0.1921Mean squared error between published probability and outcome. Lower is better; 0.25 is what you would score by predicting 50% on everything.
Calibration by probability bin
| Probability band | Probability we published | How often it actually happened | 95% interval | Fixtures |
|---|---|---|---|---|
| 0.05-0.20 | 14.8% | 10.7% | 8.0% – 14.2% | 384 |
| 0.20-0.25 | 22.8% | 17.7% | 14.6% – 21.3% | 496 |
| 0.25-0.30 | 27.4% | 27.8% | 24.7% – 31.1% | 752 |
| 0.30-0.35 | 32.1% | 30.4% | 25.7% – 35.5% | 336 |
| 0.35-0.40 | 37.4% | 35.4% | 29.6% – 41.6% | 243 |
| 0.40-0.45 | 42.8% | 51.4% | 45.2% – 57.5% | 251 |
| 0.45-0.50 | 47.4% | 48.3% | 41.0% – 55.6% | 176 |
| 0.50-0.55 | 52.5% | 57.5% | 48.8% – 65.7% | 127 |
| 0.55-0.60 | 57.5% | 61.1% | 50.8% – 70.5% | 90 |
| 0.60-0.65 | 62.3% | 68.5% | 57.1% – 78.0% | 73 |
Interval is the 95% range the observed figure could take at that sample size. Narrower means more matches in the bin.
Which markets the picks came from
A hit rate across a mixed basket is not the same claim as a hit rate on match result alone. These are the six most-used markets in each basket, with the remainder grouped, so you can judge both headline figures for yourself.
Best Picks
- Home Win or Draw47.0% of picksn = 334
- Draw or Away Win20.1% of picksn = 143
- Home Win13.0% of picksn = 92
- Over 1.5 Goals11.1% of picksn = 79
- Over 2.5 Goals4.8% of picksn = 34
- Away Win3.9% of picksn = 28
Value Analysis
- Home Win67.1% of picksn = 94
- Home Cards Under 2.57.9% of picksn = 11
- Away Cards Under 2.55.7% of picksn = 8
- Cards Under 4.55.0% of picksn = 7
- Corners Under 10.53.6% of picksn = 5
- Over 2.5 Goals2.9% of picksn = 4
- Other markets (7)7.7% of picksn = 11
2 void matches were excluded from these figures.
Monthly reports
- November 2026In progress
- October 2026
- September 2026
- August 2026
- July 2026
- June 2026
How the predictions did in November 2026
557 of 710 graded Best Picks were correct in November 2026, a hit rate of 78.5%. Value Analysis was right in 91 of 140 matches (65.0%). That is 5.0 points more than in October 2026. These are month-to-date figures up to 4 Nov 2026; the report becomes final on the 2nd of next month.
On match result, the model was right in 53.7% of 1015 matches, against 45.7% for always picking the home team.
Every prediction is graded against the result after 90 minutes, hits and misses alike, and void matches are left out. The all-time record and the method are on the Accuracy page.