Statistical Snubs
Eligible players outside the Naismith Memorial Basketball Hall of Fame whose on-field record looks like an inductee's: a model trained on every eligible career gives them at least a 50% chance. 24 players clear that line. Probabilities are out-of-fold: each player was scored by a model that never saw his own outcome.
Rankings as of 2026-11-18, as declared by the corpus that produced them.
| # | Player | Career VAL | Peak | Top-1% / led | Classes | Model |
|---|---|---|---|---|---|---|
| 1 | Jeff HornacekSG/PG · 1987–2000 · 14 seasons | 143.2 | 13.1 | 0 / 0 | 24 | 98% |
| 2 | Kevin JohnsonPG · 1988–1998 · 11 seasons | 138.5 | 18.6 | 2 / 0 | 26 | 96% |
| 3 | Andre IguodalaF · 2005–2022 · 18 seasons | 118.4 | 11.2 | 0 / 0 | 2 | 90% |
| 4 | Andre MillerPG · 2000–2016 · 17 seasons | 155.7 | 14.6 | 0 / 0 | 8 | 87% |
| 5 | Rajon RondoPG · 2007–2022 · 16 seasons | 125.9 | 17.3 | 1 / 0 | 2 | 86% |
| 6 | Deron WilliamsPG · 2006–2017 · 12 seasons | 120.8 | 17.9 | 1 / 0 | 7 | 82% |
| 7 | Larry NancePF · 1982–1994 · 13 seasons | 120.6 | 12.7 | 0 / 0 | 30 | 81% |
| 8 | Shawn MarionSG · 2000–2015 · 16 seasons | 123.7 | 15.3 | 0 / 0 | 9 | 79% |
| 9 | Mike BibbyPG · 1999–2012 · 14 seasons | 111.7 | 12.9 | 0 / 0 | 12 | 76% |
| 10 | Gus WilliamsPG · 1976–1987 · 11 seasons | 86.2 | 12.3 | 0 / 0 | 37 | 71% |
| 11 | Jimmy JonesPG/SG · 1968–1976 · 9 seasons | 87.3 | 15.4 | 1 / 0 | 48 | 70% |
| 12 | Norm NixonPG · 1978–1989 · 10 seasons | 110.9 | 15.3 | 1 / 0 | 35 | 70% |
| 13 | Paul MillsapPF · 2007–2022 · 16 seasons | 103.6 | 11.4 | 0 / 0 | 2 | 70% |
| 14 | Jason TerryG · 2000–2018 · 19 seasons | 127 | 12.3 | 0 / 0 | 6 | 65% |
| 15 | Mark JacksonPG · 1988–2004 · 17 seasons | 147.5 | 12.9 | 0 / 0 | 20 | 62% |
| 16 | Rasheed WallacePF · 1996–2013 · 16 seasons | 99.8 | 10.4 | 0 / 0 | 11 | 58% |
| 17 | Alvan AdamsPF/C · 1976–1988 · 13 seasons | 101.3 | 10.6 | 0 / 0 | 36 | 57% |
| 18 | Marques JohnsonSF · 1978–1986 · 9 seasons | 84 | 13.1 | 0 / 0 | 38 | 57% |
| 19 | Derek HarperPG · 1984–1999 · 16 seasons | 112.4 | 12.6 | 0 / 0 | 25 | 56% |
| 20 | Byron ScottSG · 1984–1997 · 14 seasons | 73.2 | 11.1 | 0 / 0 | 27 | 54% |
| 21 | Baron DavisPG · 2000–2012 · 13 seasons | 111.1 | 13.8 | 0 / 0 | 12 | 52% |
| 22 | Danny AingeSG/PG · 1982–1995 · 14 seasons | 75.5 | 10.4 | 0 / 0 | 29 | 52% |
| 23 | Marc GasolC · 2009–2021 · 13 seasons | 84.4 | 11.2 | 0 / 0 | 3 | 52% |
| 24 | Carlos BoozerPF · 2003–2015 · 13 seasons | 90.4 | 12.9 | 0 / 0 | 9 | 50% |
The same model applied to careers still in progress (appeared in 2026 or 2027), on what they have done so far. A trajectory, not a forecast: a young player's number can only rise with the seasons he has not played yet.
| # | Player | Career VAL | Peak | Top-1% / led | Model |
|---|---|---|---|---|---|
| 1 | LeBron JamesF · 2004–2027 · 24 seasons | 404.2 | 27.6 | 12 / 7 | >99% |
| 2 | Nikola JokicC · 2016–2027 · 12 seasons | 207.2 | 25.4 | 7 / 5 | >99% |
| 3 | James HardenG · 2010–2027 · 18 seasons | 249.1 | 23 | 6 / 2 | >99% |
| 4 | Stephen CurryG · 2010–2027 · 17 seasons | 240.2 | 26.4 | 5 / 2 | >99% |
| 5 | Kevin DurantF · 2008–2027 · 19 seasons | 234.5 | 23.4 | 4 / 1 | >99% |
| 6 | Giannis AntetokounmpoF · 2014–2027 · 14 seasons | 176.9 | 20.3 | 6 / 2 | >99% |
| 7 | Jimmy Butler IIIF · 2012–2026 · 15 seasons | 144.4 | 14.8 | 1 / 0 | 97% |
| 8 | Russell WestbrookG · 2009–2026 · 18 seasons | 190.1 | 20.1 | 5 / 0 | 97% |
| 9 | Kawhi LeonardF · 2012–2026 · 13 seasons | 136.2 | 15.9 | 2 / 0 | 97% |
| 10 | Al HorfordC · 2008–2027 · 19 seasons | 118 | 11.1 | 0 / 0 | 93% |
| 11 | Damian LillardG · 2013–2027 · 14 seasons | 138.7 | 14.2 | 1 / 0 | 86% |
| 12 | Shai Gilgeous-AlexanderG · 2019–2027 · 9 seasons | 104.3 | 23.4 | 3 / 1 | 86% |
| 13 | Mike ConleyG · 2008–2027 · 19 seasons | 136.9 | 13.1 | 0 / 0 | 86% |
| 14 | Paul GeorgeF · 2011–2027 · 16 seasons | 111.9 | 14.2 | 0 / 0 | 84% |
| 15 | Draymond GreenF · 2013–2027 · 15 seasons | 90.8 | 13.4 | 0 / 0 | 84% |
| 16 | Jayson TatumF · 2018–2027 · 9 seasons | 73.6 | 12.5 | 0 / 0 | 84% |
| 17 | Kyrie IrvingG · 2012–2027 · 15 seasons | 121.5 | 13.1 | 0 / 0 | 83% |
| 18 | Rudy GobertC · 2014–2027 · 14 seasons | 116.6 | 14.1 | 1 / 0 | 75% |
| 19 | Jrue HolidayG · 2010–2027 · 18 seasons | 117 | 10.2 | 0 / 0 | 72% |
| 20 | Anthony DavisF · 2013–2027 · 15 seasons | 138.1 | 15.6 | 2 / 0 | 71% |
| 21 | Karl-Anthony TownsC · 2016–2027 · 12 seasons | 103.6 | 13.1 | 0 / 0 | 65% |
| 22 | Donovan MitchellG · 2018–2027 · 10 seasons | 78.5 | 10.9 | 0 / 0 | 64% |
| 23 | Luka DoncicG · 2019–2027 · 9 seasons | 102 | 15.8 | 3 / 0 | 45% |
| 24 | Jaylen BrownG · 2017–2027 · 11 seasons | 47.1 | 7 | 0 / 0 | 42% |
| 25 | Victor WembanyamaF · 2024–2027 · 4 seasons | 29.3 | 8.5 | 1 / 1 | 40% |
Last appeared before 2026 but inside the waiting period, so no class has considered them yet.
| # | Player | Career VAL | Peak | Top-1% / led | Model |
|---|---|---|---|---|---|
| 1 | Chris PaulG · 2006–2025 · 20 seasons | 323.3 | 26.9 | 10 / 1 | >99% |
| 2 | Kyle LowryG · 2008–2025 · 18 seasons | 142.2 | 14.2 | 0 / 0 | 92% |
| 3 | Ben SimmonsPG · 2018–2025 · 6 seasons | 54.6 | 13.2 | 1 / 0 | 16% |
| 4 | Bradley BealG · 2013–2025 · 13 seasons | 65.4 | 9 | 0 / 0 | 12% |
| 5 | Patrick BeverleyPG · 2013–2024 · 11 seasons | 32.2 | 4.5 | 0 / 0 | 5% |
| 6 | Brandon ClarkeF · 2020–2025 · 5 seasons | 26.1 | 6 | 0 / 0 | 4% |
| 7 | Jae CrowderPF · 2013–2024 · 12 seasons | 27.1 | 5.3 | 0 / 0 | 4% |
| 8 | Malcolm BrogdonG · 2017–2025 · 9 seasons | 37.2 | 6.9 | 0 / 0 | 4% |
| 9 | Derrick RosePG · 2009–2024 · 14 seasons | 64.4 | 13.3 | 1 / 0 | 4% |
| 10 | Monte MorrisPG · 2019–2025 · 7 seasons | 20.5 | 5 | 0 / 0 | 4% |
One logistic regression for the NBA, fitted on 1,494 retired, eligible players of whom 146 are in the Naismith Memorial Basketball Hall of Fame (base rate 10%). Retired, last season ≤ 2023 (at least one induction class chosen since he became eligible), and ≥ 5 seasons in the VAL corpus. Inductees below the floor are excluded from training. 6 inductees fall below that floor — mostly careers played largely before or outside this league's corpus — and are not trained on. League-best seasons are ranked league-wide.
The model reads on-field value only: career and peak VAL, league-best seasons by VAL, playoff VAL and longevity. It cannot see awards voting, championships beyond playoff VAL, pre-league or international careers, eligibility bans, or character clauses. Every training player's probability is out-of-fold (scored by a model that never saw his own label). Active players (appeared in one of the last two seasons — the corpus has no retirement flag) and retired players still inside the waiting period are scored on their career to date by the full-data model — a trajectory, not a forecast. A non-inductee who is still eligible may yet be chosen, and a player still playing outside the league is not eligible however long ago he left it. Black ink is shown for context but is not a model input: its season coverage is shorter than the VAL corpus.
Held-out Brier
0.0448
base-rate guess 0.0882
Brier skill
49%
better than the base rate
AUC
0.954
ranks an inductee above a non-inductee
Folds
5
stratified, deterministic
| Predicted | Players | Mean predicted | Actually inducted |
|---|---|---|---|
| 0–10% | 1228 | 2% | 1% (17) |
| 10–20% | 83 | 14% | 24% (20) |
| 20–30% | 40 | 25% | 33% (13) |
| 30–40% | 25 | 35% | 36% (9) |
| 40–50% | 19 | 45% | 63% (12) |
| 50–60% | 17 | 56% | 47% (8) |
| 60–70% | 10 | 65% | 70% (7) |
| 70–80% | 10 | 73% | 50% (5) |
| 80–90% | 13 | 86% | 62% (8) |
| 90–100% | 49 | 98% | 96% (47) |
| Input | Pool mean | Coefficient |
|---|---|---|
| Career VAL | 33.679 | +2.4582 |
| Best 3-season VAL average | 5.352 | -0.3866 |
| Seasons in the top 1% of the league by VAL | 0.091 | -0.337 |
| Seasons as the league's VAL leader | 0.037 | +0.9918 |
| Career playoff VAL | 23.633 | +0.9762 |
| Seasons played | 9.702 | -1.001 |
| Intercept | -3.3726 |