NFL · Empirical Bayes

True-Talent Leaderboards

A raw single-season rate is a noisy guess at a player’s real ability, and the noise is worst for the smallest samples — so a naïve leaderboard is topped by whoever got lucky in the fewest tries. This one shrinks every rate toward its position-group prior by how much the sample can be trusted, and shows a 90% credible interval instead of a point. Toggle raw vs. shrunk to watch the flukes fall back to the pack.

Target success rate · 2023

Share of targets with positive EPA, shrunk within position.

Beats raw by
21.9%
lower out-of-sample error
RMSE raw → shrunk
11.7% → 9.1%
odd vs. even weeks
Split-half reliability
0.19
how repeatable the raw stat is
Stabilizes at
140
targets to trust the number
shrunkrawthe shrink90% CI
40%45%50%55%60%WR avg1Brandon AiyukSF · 10558.7%2CeeDee LambDAL · 18256.1%3Khalil ShakirBUF · 4655.2%4Tyler LockettSEA · 12455.2%5Keenan AllenLAC · 15055.1%6Amon-Ra St. BrownDET · 16555.0%7Jaylen WaddleMIA · 10454.8%8Kalif RaymondDET · 4454.7%9Tyreek HillMIA · 17254.7%10Nico CollinsHOU · 11054.7%11Adam ThielenCAR · 13854.6%12Justin JeffersonMIN · 10053.6%13Rashee RiceKC · 10253.6%14DJ MooreCHI · 13853.5%15Dontayvion WicksGB · 5853.4%16Chris OlaveNO · 13953.3%17DeVonta SmithPHI · 11353.2%18Ja'Marr ChaseCIN · 14553.2%19Jakobi MeyersLV · 10653.1%20Brandin CooksDAL · 8253.0%21Puka NacuaLA · 16052.9%22Nelson AgholorBAL · 4552.8%23Trenton IrwinCIN · 3252.7%24Brandon JohnsonDEN · 3152.4%25Josh ReynoldsDET · 6452.3%26Deebo Samuel Sr.SF · 8952.3%27A.J. BrownPHI · 15852.3%28Nick Westbrook-Ik…TEN · 4652.0%29Quez WatkinsPHI · 2152.0%30KhaDarel HodgeATL · 2352.0%31Andrei IosivasCIN · 2551.9%32Isaiah HodginsNYG · 3351.8%33Chris MooreTEN · 3551.8%34River CracraftMIA · 1251.8%35A.T. PerryNO · 1851.7%36Mike WilliamsLAC · 2651.6%37Lil'Jordan Humphr…DEN · 1951.4%38Deonte HartyBUF · 2151.4%

Each row is a player: the solid dot is the shrunk estimate, the hollow dot the raw rate, joined by the red pull of regression; the grey bar is the 90% credible interval. A hollow shrunk dot means the sample is below the stabilization line — the number is mostly the position prior. Switch to Raw rank and watch the small-sample names climb.

Target success rate · 2023 · full board

Target success rate leaderboard for the 2023 NFL season, shrunk by empirical Bayes with 90% credible intervals, ranked by the shrunk estimate.
#PlayerTeamPostargetsRawShrunk90% interval
1Brandon Aiyuk◦ provisionalSFWR10569.5%58.7%53.4%63.8%
2CeeDee LambDALWR18260.4%56.1%51.5%60.6%
3Khalil Shakir◦ provisionalBUFWR4669.6%55.2%49.2%61.2%
4Tyler Lockett◦ provisionalSEAWR12460.5%55.2%50.1%60.2%
5Keenan AllenLACWR15059.3%55.1%50.2%59.9%
6Amon-Ra St. BrownDETWR16558.8%55.0%50.3%59.7%
7Jaylen Waddle◦ provisionalMIAWR10460.6%54.8%49.5%60.0%
8Kalif Raymond◦ provisionalDETWR4468.2%54.7%48.7%60.7%
9Tyreek HillMIAWR17258.1%54.7%50.1%59.3%
10Nico Collins◦ provisionalHOUWR11060.0%54.7%49.5%59.8%
11Adam Thielen◦ provisionalCARWR13858.7%54.6%49.6%59.5%
12Justin Jefferson◦ provisionalMINWR10058.0%53.6%48.3%58.9%
13Rashee Rice◦ provisionalKCWR10257.8%53.6%48.3%58.9%
14DJ Moore◦ provisionalCHIWR13856.5%53.5%48.6%58.4%
15Dontayvion Wicks◦ provisionalGBWR5860.3%53.4%47.5%59.2%
16Chris Olave◦ provisionalNOWR13956.1%53.3%48.4%58.2%
17DeVonta Smith◦ provisionalPHIWR11356.6%53.2%48.1%58.4%
18Ja'Marr ChaseCINWR14555.9%53.2%48.4%58.1%
19Jakobi Meyers◦ provisionalLVWR10656.6%53.1%47.9%58.3%
20Brandin Cooks◦ provisionalDALWR8257.3%53.0%47.5%58.5%
21Puka NacuaLAWR16055.0%52.9%48.1%57.6%
22Nelson Agholor◦ provisionalBALWR4560.0%52.8%46.8%58.8%
23Trenton Irwin◦ provisionalCINWR3262.5%52.7%46.5%59.0%
24Brandon Johnson◦ provisionalDENWR3161.3%52.4%46.2%58.7%
25Josh Reynolds◦ provisionalDETWR6456.3%52.3%46.5%58.0%
26Deebo Samuel Sr.◦ provisionalSFWR8955.1%52.3%46.8%57.7%
27A.J. BrownPHIWR15853.8%52.3%47.5%57.0%
28Nick Westbrook-Ikhine◦ provisionalTENWR4656.5%52.0%46.0%58.0%
29Quez Watkins◦ provisionalPHIWR2161.9%52.0%45.5%58.4%
30KhaDarel Hodge◦ provisionalATLWR2360.9%52.0%45.5%58.4%
31Andrei Iosivas◦ provisionalCINWR2560.0%51.9%45.5%58.3%
32Drake London◦ provisionalATLWR11253.6%51.9%46.7%57.0%
33Isaiah Hodgins◦ provisionalNYGWR3357.6%51.8%45.6%58.1%
34Chris Moore◦ provisionalTENWR3557.1%51.8%45.6%58.0%
35Michael Thomas◦ provisionalNOWR6454.7%51.8%46.1%57.6%
36River Cracraft◦ provisionalMIAWR1266.7%51.8%45.1%58.4%
37Stefon DiggsBUFWR16152.8%51.7%47.0%56.5%
38Tee Higgins◦ provisionalCINWR7653.9%51.7%46.1%57.3%
39A.T. Perry◦ provisionalNOWR1861.1%51.7%45.2%58.2%
40Tank Dell◦ provisionalHOUWR7653.9%51.7%46.1%57.3%
41Zay Flowers◦ provisionalBALWR10953.2%51.7%46.5%56.9%
42Mike Williams◦ provisionalLACWR2657.7%51.6%45.2%58.0%
43Michael Wilson◦ provisionalARIWR5954.2%51.6%45.8%57.4%
44Michael PittmanINDWR15852.5%51.6%46.8%56.3%
45Jalen Tolbert◦ provisionalDALWR3655.6%51.5%45.3%57.7%
46Mike Evans◦ provisionalTBWR13752.5%51.5%46.6%56.4%
47Lil'Jordan Humphrey◦ provisionalDENWR1957.9%51.4%44.9%57.9%
48Noah Brown◦ provisionalHOUWR5653.6%51.4%45.5%57.2%
49Deonte Harty◦ provisionalBUFWR2157.1%51.4%44.9%57.8%
50Wan'Dale Robinson◦ provisionalNYGWR7852.6%51.2%45.7%56.8%
51Demarcus Robinson◦ provisionalLAWR3953.8%51.2%45.1%57.4%
52Romeo Doubs◦ provisionalGBWR9652.1%51.1%45.8%56.5%
53Josh Downs◦ provisionalINDWR9852.0%51.1%45.8%56.5%
54Jamison Crowder◦ provisionalWASWR2055.0%51.1%44.6%57.5%
55Kyle Philips◦ provisionalTENWR2254.5%51.0%44.6%57.5%
56Darius Slayton◦ provisionalNYGWR7951.9%51.0%45.5%56.5%
57Christian Kirk◦ provisionalJAXWR8551.8%51.0%45.5%56.4%
58Cooper Kupp◦ provisionalLAWR9751.5%50.9%45.6%56.3%
59DK Metcalf◦ provisionalSEAWR11951.3%50.8%45.7%56.0%
60Ray-Ray McCloud◦ provisionalSFWR1553.3%50.8%44.2%57.4%
61Gabe Davis◦ provisionalBUFWR8251.2%50.8%45.3%56.3%
62Braxton Berrios◦ provisionalMIAWR3351.5%50.7%44.4%56.9%
63Jauan Jennings◦ provisionalSFWR3351.5%50.7%44.4%56.9%
64George Pickens◦ provisionalPITWR10650.9%50.7%45.5%55.9%
65Amari Cooper◦ provisionalCLEWR13050.8%50.6%45.6%55.6%
66Michael Gallup◦ provisionalDALWR5750.9%50.6%44.8%56.5%
67Diontae Johnson◦ provisionalPITWR8750.6%50.5%45.1%56.0%
68Isaiah McKenzie◦ provisionalINDWR1450.0%50.4%43.8%57.1%
69Richie James◦ provisionalKCWR1450.0%50.4%43.8%57.1%
70Olamide Zaccheaus◦ provisionalPHIWR2050.0%50.4%43.9%56.9%
71Mack Hollins◦ provisionalATLWR3050.0%50.4%44.1%56.7%
72Rashod Bateman◦ provisionalBALWR5650.0%50.3%44.5%56.2%
73Jamal Agnew◦ provisionalJAXWR2147.6%50.1%43.6%56.6%
74Dyami Brown◦ provisionalWASWR2347.8%50.1%43.7%56.5%
75Parker Washington◦ provisionalJAXWR2147.6%50.1%43.6%56.6%
76Ronnie Bell◦ provisionalSFWR1346.2%50.1%43.5%56.8%
77Jake Bobo◦ provisionalSEAWR2548.0%50.1%43.7%56.5%
78Courtland Sutton◦ provisionalDENWR9149.5%50.1%44.7%55.5%
79Jayden Reed◦ provisionalGBWR9549.5%50.1%44.7%55.4%
80Chris Godwin Jr.◦ provisionalTBWR13149.6%50.1%45.1%55.1%
81Calvin Ridley◦ provisionalJAXWR13749.6%50.1%45.1%55.0%
82Tyler Boyd◦ provisionalCINWR9849.0%49.9%44.5%55.2%
83Odell Beckham Jr.◦ provisionalBALWR6448.4%49.9%44.1%55.6%
84Brandon Powell◦ provisionalMINWR4447.7%49.8%43.8%55.9%
85Jalin Hyatt◦ provisionalNYGWR4047.5%49.8%43.7%56.0%
86Cedrick Wilson Jr.◦ provisionalMIAWR3847.4%49.8%43.7%56.0%
87John Metchie III◦ provisionalHOUWR3046.7%49.8%43.5%56.1%
88Byron Pringle◦ provisionalWASWR2245.5%49.8%43.4%56.3%
89Trent Sherfield◦ provisionalBUFWR2245.5%49.8%43.4%56.3%
90Mecole Hardman◦ provisionalKCWR2445.8%49.8%43.4%56.2%
91Malik Heath◦ provisionalGBWR2445.8%49.8%43.4%56.2%
92Scott Miller◦ provisionalATLWR1643.8%49.8%43.2%56.4%
93KaVontae Turpin◦ provisionalDALWR1844.4%49.8%43.3%56.3%
94Ben Skowronek◦ provisionalLAWR1241.7%49.8%43.1%56.5%
95Jaxon Smith-Njigba◦ provisionalSEAWR9348.4%49.6%44.3%55.0%
96Jerry Jeudy◦ provisionalDENWR8748.3%49.6%44.2%55.1%
97Jahan Dotson◦ provisionalWASWR8348.2%49.6%44.1%55.1%
98DeVante Parker◦ provisionalNEWR5547.3%49.6%43.7%55.5%
99Kendrick Bourne◦ provisionalNEWR5547.3%49.6%43.7%55.5%
100Justin Watson◦ provisionalKCWR5347.2%49.6%43.7%55.5%
101Christian Watson◦ provisionalGBWR5347.2%49.6%43.7%55.5%
102Hunter Renfrow◦ provisionalLVWR3746.0%49.5%43.4%55.7%
103Terrace Marshall Jr.◦ provisionalCARWR3345.5%49.5%43.3%55.8%
104Alex Erickson◦ provisionalLACWR2944.8%49.5%43.2%55.8%
105David Bell◦ provisionalCLEWR2343.5%49.5%43.1%55.9%
106Jameson Williams◦ provisionalDETWR4245.2%49.3%43.2%55.4%
107Tre Tucker◦ provisionalLVWR3444.1%49.2%43.0%55.5%
108Curtis Samuel◦ provisionalWASWR9147.3%49.2%43.8%54.6%
109Ty Montgomery◦ provisionalNEWR1233.3%49.1%42.5%55.8%
110Quentin Johnston◦ provisionalLACWR6746.3%49.1%43.4%54.8%
111Alec Pierce◦ provisionalINDWR6546.2%49.1%43.4%54.9%
112JuJu Smith-Schuster◦ provisionalNEWR4744.7%49.0%43.0%55.0%
113Greg Dortch◦ provisionalARIWR4143.9%49.0%42.9%55.1%
114Marvin Mims Jr.◦ provisionalDENWR3342.4%48.9%42.7%55.2%
115Donovan Peoples-Jones◦ provisionalDETWR2540.0%48.9%42.5%55.3%
116Tutu Atwell◦ provisionalLAWR6845.6%48.9%43.2%54.6%
117Zay Jones◦ provisionalJAXWR6445.3%48.9%43.1%54.6%
118Jalen Guyton◦ provisionalLACWR2138.1%48.9%42.4%55.4%
119Tim Jones◦ provisionalJAXWR1936.8%48.9%42.4%55.4%
120Cedric Tillman◦ provisionalCLEWR4443.2%48.7%42.7%54.8%
121Skyy Moore◦ provisionalKCWR3842.1%48.7%42.5%54.9%
122Jordan Addison◦ provisionalMINWR10846.3%48.7%43.5%53.9%
123Tyler Scott◦ provisionalCHIWR3240.6%48.6%42.4%54.9%
124Josh Palmer◦ provisionalLACWR6144.3%48.6%42.8%54.4%
125Allen Robinson◦ provisionalPITWR4942.9%48.5%42.5%54.5%
126Allen Lazard◦ provisionalNYJWR4942.9%48.5%42.5%54.5%
127Davante AdamsLVWR17546.9%48.5%43.9%53.1%
128Van Jefferson◦ provisionalATLWR4341.9%48.5%42.4%54.5%
129Deven Thompkins◦ provisionalTBWR2536.0%48.3%41.9%54.7%
130Julio Jones◦ provisionalPHIWR1931.6%48.2%41.7%54.8%
131Samori Toure◦ provisionalGBWR1931.6%48.2%41.7%54.8%
132Robert Woods◦ provisionalHOUWR7544.0%48.2%42.6%53.8%
133K.J. Osborn◦ provisionalMINWR7544.0%48.2%42.6%53.8%
134Derius Davis◦ provisionalLACWR1729.4%48.2%41.7%54.8%
135Kadarius Toney◦ provisionalKCWR3839.5%48.1%42.0%54.3%
136Darnell Mooney◦ provisionalCHIWR6142.6%48.1%42.3%53.9%
137Treylon Burks◦ provisionalTENWR3036.7%48.0%41.8%54.4%
138Calvin Austin III◦ provisionalPITWR3036.7%48.0%41.8%54.4%
139DeAndre Hopkins◦ provisionalTENWR13745.3%47.9%43.0%52.8%
140Lynn Bowden◦ provisionalNOWR1625.0%47.9%41.3%54.5%
141Parris Campbell◦ provisionalNYGWR2733.3%47.7%41.4%54.1%
142Marquez Valdes-Scantling◦ provisionalKCWR4238.1%47.6%41.6%53.7%
143Xavier Hutchinson◦ provisionalHOUWR1926.3%47.6%41.1%54.1%
144Zach Pascal◦ provisionalARIWR1520.0%47.5%41.0%54.1%
145Keelan Doss◦ provisionalLACWR1315.4%47.5%40.9%54.1%
146DeMario Douglas◦ provisionalNEWR7941.8%47.3%41.8%52.9%
147Rashid Shaheed◦ provisionalNOWR7541.3%47.3%41.7%52.9%
148Randall Cobb◦ provisionalNYJWR1822.2%47.3%40.8%53.8%
149Jalen Reagor◦ provisionalNEWR2326.1%47.0%40.6%53.5%
150Chase Claypool◦ provisionalMIAWR2123.8%47.0%40.6%53.5%
151Xavier Gipson◦ provisionalNYJWR3834.2%47.0%40.9%53.2%
152Terry McLaurin◦ provisionalWASWR13243.2%46.9%42.0%51.9%
153Marquise Goodwin◦ provisionalCLEWR137.7%46.9%40.3%53.5%
154Sterling Shepard◦ provisionalNYGWR2222.7%46.7%40.3%53.2%
155Rondale Moore◦ provisionalARIWR6338.1%46.6%40.9%52.4%
156Elijah Moore◦ provisionalCLEWR10441.3%46.6%41.4%51.8%
157DJ Chark◦ provisionalCARWR6637.9%46.4%40.8%52.2%
158Tyquan Thornton◦ provisionalNEWR2321.7%46.4%40.0%52.9%
159Garrett WilsonNYJWR16842.9%46.3%41.7%51.0%
160Trey Palmer◦ provisionalTBWR6937.7%46.3%40.6%51.9%
161Marquise Brown◦ provisionalARIWR10438.5%45.4%40.1%50.6%
162Jonathan Mingo◦ provisionalCARWR8532.9%43.9%38.5%49.3%

How the shrinkage works

Two estimators

Rate stats (completion %, success rate, catch rate) use a beta-binomial model: a Beta(α, β) prior fit by marginal likelihood over each position group, then a Beta posterior per player. Per-play averages (EPA, CPOE, yards) use a normal-normal model with DerSimonian–Laird between-player variance. Both pull each player toward their group by exactly how thin their sample is.

Does it help? & the fine print

The trust panel’s numbers come from a leakage-free odd/even-week holdout: fit on odd weeks, predict even-week raw. Shrinkage lowers out-of-sample error for every stat. Priors are fit per season and per position (WR and TE separately), so a TE’s baseline isn’t a skill. Regular season only, 2016–2025. Rushing and receiving efficiency are heavily scheme-driven — read the wide bands as the honesty they are.

Source: nflverse play-by-play. Counted and computed deterministically — never modeled by a language model. Built by build_nfl_leaderboards.py (byte-reproducible).