Cycling race predictor · one-day race

Münsterland Giro 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 3 October 2026 1 reading 152 riders priced models retrained 72bc1bd857 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

Münsterland Giro on its own recent editions
sprint0.05
mountain0.06
hilly0.24
rolling0.35
break0.31
TT0.00
References: Münsterland Giro (2025); Münsterland Giro (2024); Münsterland Giro (2023); Münsterland Giro (2021); Münsterland Giro (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): Philipsen Jasper 19.3%; Brennan Matthew 17.7%; De Lie Arnaud 12.0%; Kooij Olav 7.2%; Merlier Tim 6.1%

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 107% — 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
Philipsen JasperAlpecin-Premier Tech19.3%15.2%19.1%n/a––
Brennan MatthewTeam Visma | Lease a Bike17.7%26.6%14.4%n/a––
De Lie ArnaudLotto-Intermarché12.0%10.2%11.7%n/a––
Kooij OlavDecathlon CMA CGM Team7.2%8.4%6.4%n/a––
Merlier TimSoudal Quick-Step6.1%7.1%5.5%n/a––
Meeus JordiRed Bull-BORA-hansgrohe5.8%5.3%5.5%n/a––
Pedersen MadsLidl-Trek5.0%6.5%4.3%n/a––
Groenewegen DylanUnibet Rose Rockets3.7%5.3%3.0%n/a––
de Kleijn ArvidTudor Pro Cycling Team2.9%1.9%2.9%n/a––
Wærenskjold SørenUno-X Mobility2.8%2.7%2.6%n/a––
Fretin MilanCofidis2.2%1.7%2.1%n/a––
Vernon EthanNSN Cycling Team2.1%2.3%1.9%n/a––
van Poppel DannyRed Bull-BORA-hansgrohe1.9%0.4%2.1%n/a––
Biesterbos FritsTeam Picnic PostNL1.8%1.5%1.7%n/a––
Walscheid MaxLidl-Trek1.6%1.5%1.5%n/a––
Bol CeesDecathlon CMA CGM Team1.4%0.8%1.5%n/a––
Moschetti MatteoPinarello-Q36.5 Pro Cycling Team1.4%1.3%1.3%n/a––
Askey LewisNSN Cycling Team1.2%0.4%1.4%n/a––
Aniolkowski StanislawCofidis1.1%1.6%0.9%n/a––
Lamperti LukeEF Education-EasyPost1.0%0.7%1.0%n/a––
Pluimers RickTudor Pro Cycling Team1.0%0.4%1.1%n/a––
Münsterland Giro on its own recent editions — top 30, all heads
#RiderBlendCascade LambdaRankPodiumTop 15 Market odds
1Philipsen Jasper19.3%15.2%19.1%32.5%59.0%n/a
2Brennan Matthew17.7%26.6%14.4%48.1%67.1%n/a
3De Lie Arnaud12.0%10.2%11.7%26.2%59.7%n/a
4Kooij Olav7.2%8.4%6.4%23.2%43.9%n/a
5Merlier Tim6.1%7.1%5.5%18.8%43.1%n/a
6Meeus Jordi5.8%5.3%5.5%18.8%48.7%n/a
7Pedersen Mads5.0%6.5%4.3%18.2%43.1%n/a
8Groenewegen Dylan3.7%5.3%3.0%13.4%38.2%n/a
9de Kleijn Arvid2.9%1.9%2.9%11.0%35.8%n/a
10Wærenskjold Søren2.8%2.7%2.6%9.0%40.2%n/a
11Fretin Milan2.2%1.7%2.1%9.6%40.6%n/a
12Vernon Ethan2.1%2.3%1.9%9.4%32.2%n/a
13van Poppel Danny1.9%0.4%2.1%7.2%42.0%n/a
14Biesterbos Frits1.8%1.5%1.7%9.5%49.1%n/a
15Walscheid Max1.6%1.5%1.5%9.1%27.6%n/a
16Bol Cees1.4%0.8%1.5%4.0%17.7%n/a
17Moschetti Matteo1.4%1.3%1.3%9.6%43.5%n/a
18Askey Lewis1.2%0.4%1.4%3.9%23.0%n/a
19Aniolkowski Stanislaw1.1%1.6%0.9%7.4%40.0%n/a
20Lamperti Luke1.0%0.7%1.0%4.0%29.5%n/a
21Pluimers Rick1.0%0.4%1.1%4.6%38.5%n/a
22De Schuyteneer Steffen0.9%1.2%0.8%4.9%31.3%n/a
23Thijssen Gerben0.6%0.4%0.6%4.2%41.7%n/a
24Hobbs Noah0.5%0.3%0.6%3.3%22.8%n/a
25Hofstetter Hugo0.4%0.2%0.4%2.0%35.4%n/a
26Gachignard Thomas0.3%0.1%0.4%0.5%7.7%n/a
27Marit Arne0.3%0.2%0.3%1.8%23.4%n/a
28Taminiaux Lionel0.3%0.0%0.3%1.3%8.5%n/a
29Turgis Anthony0.3%0.1%0.3%0.6%18.4%n/a
30Van Asbroeck Tom0.3%0.1%0.3%0.6%17.9%n/a

After the race

Result — won by Kooij Olav

PosRiderTeamOwn history win p
1Kooij OlavDecathlon CMA CGM Team7.2%
2Meeus JordiRed Bull-BORA-hansgrohe5.8%
3Biesterbos FritsTeam Picnic PostNL1.8%
4Turgis AnthonyTeam TotalEnergies0.3%
5Hofstetter HugoNSN Cycling Team0.4%
6Dauphin FlorianTeam TotalEnergies0.1%
7Fretin MilanCofidis2.2%
8Philipsen JasperAlpecin-Premier Tech19.3%
9Wærenskjold SørenUno-X Mobility2.8%
10de Kleijn ArvidTudor Pro Cycling Team2.9%

Scoring — probability given to the actual winner

ReadingBlendCascade LambdaRankMarket devig
Own history7.17%8.40%6.40%–

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.