Cycling race predictor · one-day race

Gooikse Pijl settled

One day, one result: the production stack priced the whole field under 1 course reading, against the market's line where one was captured. A one-day race is its own best reference — the main reading is built from this race's own recent editions.

Raced 20 September 2026 1 reading 127 riders priced models retrained 75c6e7af51 market snapshot no capture

The fork

1 reading of the same road

Course profile is an input the model cannot see from a map — it is set from reference races. The main reading averages this race's own last editions, so the terrain and the kind of rider it selects come from the race's own history; any alternate reading swaps in an archetype set to ask what a different day would do to the same field.

Own history

Gooikse Pijl on its own recent editions
sprint0.19
mountain0.01
hilly0.60
rolling0.07
break0.13
TT0.00
References: Gooikse Pijl (2025); Gooikse Pijl (2024); Gooikse Pijl (2023); Gooikse Pijl (2022); Gooikse Pijl (2019)
The race read on its own recent history: the profile is the average of this race's last 5 editions, so the terrain and the kind of rider it selects come from the race itself rather than from an archetype.
Top 5 (blend): Meeus Jordi 22.2%; Groenewegen Dylan 20.3%; Vernon Ethan 18.0%; Wærenskjold Søren 14.5%; Kogut Oded 7.7%

The board

Win probabilities across the heads

Blend is the production price (cascade × LambdaRank, DNF-adjusted at the pricing layer); Cascade and LambdaRank are the two underlying heads shown for the main reading. The market columns are the devigged win line, present as the information benchmark the model is scored against.

Read "Max edge" as directional, not as a price. The blend is a set of per-rider marginals and does not sum to one book — across this field each reading totals own history 132% — while the devigged market column sums to exactly 100%. Putting the two side by side flatters the model, and Max edge is inflated by about that factor. Of our heads only the LambdaRank one is natively book-preserving.

RiderTeamBlendCascadeLambdaRankMarket oddsMarket devigMax edge
Meeus JordiRed Bull-BORA-hansgrohe22.2%26.1%15.8%n/a––
Groenewegen DylanUnibet Rose Rockets20.3%29.4%13.0%n/a––
Vernon EthanNSN Cycling Team18.0%15.2%14.3%n/a––
Wærenskjold SørenUno-X Mobility14.5%10.4%12.0%n/a––
Kogut OdedNSN Cycling Team7.7%9.2%5.4%n/a––
De Schuyteneer SteffenLotto-Intermarché7.1%6.1%5.6%n/a––
Hobbs NoahEF Education-EasyPost5.8%9.4%3.5%n/a––
Thijssen GerbenAlpecin-Premier Tech4.1%1.8%3.7%n/a––
Lamperti LukeEF Education-EasyPost3.9%1.9%3.4%n/a––
Biesterbos FritsTeam Picnic PostNL3.2%1.7%2.8%n/a––
Kanter MaxXDS Astana Team3.2%3.7%2.3%n/a––
Mihkels MadisEF Education-EasyPost3.0%2.8%2.3%n/a––
van Dijke TimRed Bull-BORA-hansgrohe2.6%2.0%2.1%n/a––
Marit ArneRed Bull-BORA-hansgrohe2.3%1.7%1.8%n/a––
Teunissen MikeXDS Astana Team1.9%1.5%1.6%n/a––
Plowright JensenAlpecin-Premier Tech1.4%0.8%1.2%n/a––
Dekker DavidBEAT CC p/b Saxo1.2%0.5%1.1%n/a––
Gooikse Pijl on its own recent editions — top 30, all heads
#RiderBlendCascade LambdaRankPodiumTop 15 Market odds
1Meeus Jordi22.2%26.1%15.8%44.7%78.5%n/a
2Groenewegen Dylan20.3%29.4%13.0%54.3%81.8%n/a
3Vernon Ethan18.0%15.2%14.3%44.6%74.6%n/a
4Wærenskjold Søren14.5%10.4%12.0%28.1%69.5%n/a
5Kogut Oded7.7%9.2%5.4%25.6%61.4%n/a
6De Schuyteneer Steffen7.1%6.1%5.6%17.9%59.4%n/a
7Hobbs Noah5.8%9.4%3.5%24.4%65.9%n/a
8Thijssen Gerben4.1%1.8%3.7%9.2%54.5%n/a
9Lamperti Luke3.9%1.9%3.4%8.5%45.7%n/a
10Biesterbos Frits3.2%1.7%2.8%6.7%40.7%n/a
11Kanter Max3.2%3.7%2.3%16.4%49.2%n/a
12Mihkels Madis3.0%2.8%2.3%9.4%44.9%n/a
13van Dijke Tim2.6%2.0%2.1%7.9%33.3%n/a
14Marit Arne2.3%1.7%1.8%8.0%48.5%n/a
15Teunissen Mike1.9%1.5%1.6%6.1%37.6%n/a
16Plowright Jensen1.4%0.8%1.2%11.7%38.0%n/a
17Dekker David1.2%0.5%1.1%4.0%53.2%n/a
18Borgo Alessandro0.7%0.5%0.6%3.4%33.8%n/a
19Stewart Jake0.7%0.2%0.7%2.7%26.8%n/a
20Dupont Timothy0.7%0.4%0.6%3.1%34.8%n/a
21Taminiaux Lionel0.7%0.3%0.6%4.0%20.7%n/a
22Müller Tobias0.6%0.4%0.5%4.0%30.8%n/a
23van Uden Casper0.5%0.5%0.4%4.5%30.0%n/a
24Bevort Carl-Frederik0.5%0.5%0.4%5.2%37.6%n/a
25Van Asbroeck Tom0.5%0.3%0.4%2.8%47.7%n/a
26Etxeberria Haimar0.3%0.6%0.2%2.5%15.1%n/a
27Capiot Amaury0.3%0.6%0.1%2.3%29.4%n/a
28Fox Matthew0.3%0.1%0.3%0.6%21.7%n/a
29Flynn Sean0.3%0.2%0.2%1.2%17.3%n/a
30Kurits Karl0.3%0.6%0.1%2.3%23.7%n/a

After the race

Result — won by Kanter Max

PosRiderTeamOwn history win p
1Kanter MaxXDS Astana Team3.2%
2Biesterbos FritsTeam Picnic PostNL3.2%
3Meeus JordiRed Bull-BORA-hansgrohe22.2%
4Vernon EthanNSN Cycling Team18.0%
5Van Asbroeck TomNSN Cycling Team0.5%
6Hesters JulesTeam Flanders-Baloise0.1%
7De Schuyteneer SteffenLotto-Intermarché7.1%
8Wærenskjold SørenUno-X Mobility14.5%
9Borgo AlessandroBahrain Victorious0.7%
10Thijssen GerbenAlpecin-Premier Tech4.1%

Scoring — probability given to the actual winner

ReadingBlendCascade LambdaRankMarket devig
Own history3.16%3.65%2.26%–

Result rows are joined to the boards by FirstCycling rider id through the riders table. 0 row(s) needed the normalised-name fallback; 2 finisher(s) could not be matched at all.