Data-Driven Sailing Home Under the hood ICSA ISSA
A statistics project on college sailing results, 2008 to 2026

College sailing ratings

I scrape results from the ICSA and ISSA scoring sites, fit a rating to every sailor, and test how well it predicts races it hasn't seen. 1.5 million boat-race results since 2008.

100K+
Training races
24K+
Sailors modeled
13.7M
Parameters
70%
Held‑out accuracy

Predictions

Win probability from 5,000 simulated regattas on the predicted lineups. One event per weekend, the one with the strongest field.

Oct 4
SHU Trophy
Sacred Heart University · 7 schools
2
30%
Sacred Heart University
1
43%
Brandeis University
3
14%
Williams College
Oct 10–11
Stu Nelson @ Connecticut College 2026
Connecticut College · 15 schools
2
27%
Yale University
1
31%
Stanford University
3
11%
Tulane University
Oct 10–11
Sister Esther Whalen Trophy
Salve Regina · 16 schools
2
16%
Brown University
1
24%
Boston College
3
12%
Harvard University
Oct 17–18
Captain Hurst
Dartmouth College · 10 schools
2
18%
Dartmouth College
1
20%
Brown University
3
15%
Boston College
Oct 24–25
Oberg Trophy
NU/MIT · 12 schools
2
22%
Dartmouth College
1
32%
Brown University
3
19%
Roger Williams University
Oct 31
Nickerson Trophy
Tufts University · 12 schools
2
19%
Dartmouth College
1
20%
Brown University
3
14%
Boston College

Predicted lineups and simulated standings for every regatta.

Ratings over time

Best sailor in each of the last five graduating classes, weekly rating over their career
2.53.03.54.04.55.05.56.0201520162017201820192020202120222023202420252026Shawn Harvey (class of 2022): peak 5.10Robert Bragg (class of 2023): peak 5.04Lachlain Mcgranahan (class of 2024): peak 5.04Jack Egan (class of 2025): peak 5.04Guthrie Braun (class of 2026): peak 5.28Guthrie Braun ’26Shawn Harvey ’22Robert Bragg ’23Lachlain Mcgranahan ’24Jack Egan ’25

ICSA. The sailor with the highest peak rating in each class; the line is their rating every week they were rated.

Program rank: average rating of each school's two best active skippers
1234567891011+Jun 22Dec 22Jun 23Dec 23Jun 24Dec 24Jun 25Dec 25Jun 26Oct 26Stanford: rank 1, rating 5.15 (Jun 2022)Stanford: rank 1, rating 5.15 (Dec 2022)Stanford: rank 1, rating 5.09 (Jun 2023)Stanford: rank 2, rating 5.03 (Dec 2023)Stanford: rank 2, rating 4.96 (Jun 2024)Stanford: rank 1, rating 5.06 (Dec 2024)Stanford: rank 1, rating 5.12 (Jun 2025)Stanford: rank 1, rating 5.10 (Dec 2025)Stanford: rank 1, rating 5.20 (Jun 2026)Stanford: rank 1, rating 5.20 (Oct 2026)Brown: rank 7, rating 4.40 (Jun 2022)Brown: rank 5, rating 4.62 (Dec 2022)Brown: rank 4, rating 4.70 (Jun 2023)Brown: rank 4, rating 4.80 (Dec 2023)Brown: rank 4, rating 4.86 (Jun 2024)Brown: rank 4, rating 4.86 (Dec 2024)Brown: rank 4, rating 4.87 (Jun 2025)Brown: rank 2, rating 5.00 (Dec 2025)Brown: rank 2, rating 5.14 (Jun 2026)Brown: rank 2, rating 5.13 (Oct 2026)Harvard: rank 3, rating 4.88 (Jun 2022)Harvard: rank 3, rating 4.95 (Dec 2022)Harvard: rank 2, rating 4.95 (Jun 2023)Harvard: rank 1, rating 5.05 (Dec 2023)Harvard: rank 1, rating 5.07 (Jun 2024)Harvard: rank 2, rating 5.05 (Dec 2024)Harvard: rank 2, rating 4.89 (Jun 2025)Harvard: rank 3, rating 4.95 (Dec 2025)Harvard: rank 3, rating 4.89 (Jun 2026)Harvard: rank 3, rating 4.89 (Oct 2026)Dartmouth: rank 5, rating 4.62 (Jun 2022)Dartmouth: rank 4, rating 4.64 (Dec 2022)Dartmouth: rank 5, rating 4.60 (Jun 2023)Dartmouth: rank 5, rating 4.64 (Dec 2023)Dartmouth: rank 3, rating 4.87 (Jun 2024)Dartmouth: rank 3, rating 4.87 (Dec 2024)Dartmouth: rank 10, rating 4.34 (Jun 2025)Dartmouth: rank 9, rating 4.39 (Dec 2025)Dartmouth: rank 6, rating 4.52 (Jun 2026)Dartmouth: rank 5, rating 4.59 (Oct 2026)Yale: rank 2, rating 4.97 (Jun 2022)Yale: rank 2, rating 5.03 (Dec 2022)Yale: rank 3, rating 4.81 (Jun 2023)Yale: rank 3, rating 4.88 (Dec 2023)Yale: rank 5, rating 4.85 (Jun 2024)Yale: rank 5, rating 4.84 (Dec 2024)Yale: rank 3, rating 4.88 (Jun 2025)Yale: rank 4, rating 4.88 (Dec 2025)Yale: rank 10, rating 4.37 (Jun 2026)Yale: rank 10, rating 4.40 (Oct 2026)StanfordYaleHarvardDartmouthBrownStanfordBrownHarvardDartmouthYale

Ranked among all ICSA programs at the end of each season. Schools shown were top three at least once; a line that reaches the bottom row is outside the top ten.

Method

Every sailor gets a skill rating for each week they race, θ[sailor, week]. I fit the ratings so the observed finishing orders are as likely as possible under a Plackett–Luce model, which handles a full finishing order rather than just win or loss. Penalties on week-to-week change keep a rating from jumping on one regatta. About 13.7 million parameters, trained in PyTorch.

The Boat Speed Analyzer uses the same data. It compares a school's fleet-race results across two time windows and tests whether the difference is larger than race-to-race noise.

Accuracy

I held out a random 1 in 20 regattas before fitting. On those races the model picks the faster of two boats 70% of the time. Forecasts a full season ahead, and the comparison with Elo and simpler baselines, are on the methodology page.

70%
of boat pairs ordered correctly on held-out races

Why

More

See the rankings How it's built Boat speed analyzer College recruiting guide Summer transition analysis