Cycling race predictor · one-day race

Flandrien 0.0 Classic 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 19 September 2026 1 reading 153 riders priced models retrained d911de60f7 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

Flandrien 0.0 Classic on its own recent editions
sprint0.16
mountain0.10
hilly0.03
rolling0.56
break0.16
TT0.00
References: SUPER 8 Classic (2025); SUPER 8 Classic (2024); SUPER 8 Classic (2023); SUPER 8 Classic (2022); SUPER 8 Classic (2021)
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): Merlier Tim 16.4%; Meeus Jordi 12.2%; Pithie Laurence 9.8%; De Lie Arnaud 8.3%; Philipsen Jasper 7.5%

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 115% — 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
Merlier TimSoudal Quick-Step16.4%29.4%11.0%n/a––
Meeus JordiRed Bull-BORA-hansgrohe12.2%10.2%11.2%n/a––
Pithie LaurenceRed Bull-BORA-hansgrohe9.8%9.7%8.6%n/a––
De Lie ArnaudLotto-Intermarché8.3%8.9%7.1%n/a––
Philipsen JasperAlpecin-Premier Tech7.5%7.3%6.5%n/a––
Girmay BiniamNSN Cycling Team5.6%5.7%4.9%n/a––
Wærenskjold SørenUno-X Mobility4.1%2.9%3.9%n/a––
Vermeersch FlorianUAE Team Emirates-XRG3.7%3.2%3.3%n/a––
Gruel ThibaudGroupama-FDJ United2.5%2.6%2.1%n/a––
Vernon EthanNSN Cycling Team2.1%2.1%1.8%n/a––
Nys ThibauLidl-Trek2.1%3.3%1.5%n/a––
Lamperti LukeEF Education-EasyPost1.9%1.4%1.8%n/a––
Del Grosso TiborAlpecin-Premier Tech1.9%1.2%1.8%n/a––
van Poppel DannyRed Bull-BORA-hansgrohe1.8%1.2%1.7%n/a––
Fretin MilanCofidis1.7%1.7%1.5%n/a––
Pluimers RickTudor Pro Cycling Team1.6%0.3%1.8%n/a––
Askey LewisNSN Cycling Team1.6%1.9%1.3%n/a––
Bittner PavelTeam Picnic PostNL1.5%2.1%1.2%n/a––
Turgis AnthonyTeam TotalEnergies1.4%0.2%1.5%n/a––
Berckmoes JennoLotto-Intermarché1.4%1.1%1.3%n/a––
Kanter MaxXDS Astana Team1.2%2.3%0.8%n/a––
Kubis LukasUnibet Rose Rockets1.2%0.8%1.1%n/a––
Adrià RogerMovistar Team1.1%0.8%1.1%n/a––
Mozzato LucaTudor Pro Cycling Team1.0%0.3%1.1%n/a––
Flandrien 0.0 Classic on its own recent editions — top 30, all heads
#RiderBlendCascade LambdaRankPodiumTop 15 Market odds
1Merlier Tim16.4%29.4%11.0%43.0%59.1%n/a
2Meeus Jordi12.2%10.2%11.2%25.4%50.5%n/a
3Pithie Laurence9.8%9.7%8.6%24.0%56.7%n/a
4De Lie Arnaud8.3%8.9%7.1%20.3%46.0%n/a
5Philipsen Jasper7.5%7.3%6.5%18.6%45.3%n/a
6Girmay Biniam5.6%5.7%4.9%14.2%41.2%n/a
7Wærenskjold Søren4.1%2.9%3.9%8.7%30.7%n/a
8Vermeersch Florian3.7%3.2%3.3%8.8%32.0%n/a
9Gruel Thibaud2.5%2.6%2.1%8.8%38.6%n/a
10Vernon Ethan2.1%2.1%1.8%6.8%24.1%n/a
11Nys Thibau2.1%3.3%1.5%9.6%33.8%n/a
12Lamperti Luke1.9%1.4%1.8%5.2%28.9%n/a
13Del Grosso Tibor1.9%1.2%1.8%5.2%30.5%n/a
14van Poppel Danny1.8%1.2%1.7%7.6%41.4%n/a
15Fretin Milan1.7%1.7%1.5%7.2%35.6%n/a
16Pluimers Rick1.6%0.3%1.8%3.9%34.1%n/a
17Askey Lewis1.6%1.9%1.3%8.2%39.7%n/a
18Bittner Pavel1.5%2.1%1.2%8.3%34.2%n/a
19Turgis Anthony1.4%0.2%1.5%1.7%27.8%n/a
20Berckmoes Jenno1.4%1.1%1.3%7.1%44.1%n/a
21Kanter Max1.2%2.3%0.8%9.2%33.0%n/a
22Kubis Lukas1.2%0.8%1.1%4.2%36.5%n/a
23Adrià Roger1.1%0.8%1.1%2.6%25.8%n/a
24Mozzato Luca1.0%0.3%1.1%3.7%29.1%n/a
25Cosnefroy Benoît1.0%0.6%1.0%2.8%27.3%n/a
26Teutenberg Tim Torn1.0%1.7%0.7%4.4%24.2%n/a
27Morgado António0.9%0.9%0.8%2.2%22.2%n/a
28Grisel Matys0.9%0.6%0.8%4.0%30.8%n/a
29Teunissen Mike0.8%0.4%0.8%3.2%29.3%n/a
30Trentin Matteo0.8%0.6%0.7%1.3%34.1%n/a

After the race

Result — won by Pedersen Henrik

PosRiderTeamOwn history win p
1Pedersen HenrikUno-X Mobility0.1%
2Pithie LaurenceRed Bull-BORA-hansgrohe9.8%
3Vermeersch FlorianUAE Team Emirates-XRG3.7%
4Berckmoes JennoLotto-Intermarché1.4%
5Teutenberg Tim TornLidl-Trek1.0%
6Gruel ThibaudGroupama-FDJ United2.5%
7Kubis LukasUnibet Rose Rockets1.2%
8De Gendt AiméPinarello-Q36.5 Pro Cycling Team0.1%
9Lamperti LukeEF Education-EasyPost1.9%
10Huens AxelGroupama-FDJ United0.4%

Scoring — probability given to the actual winner

ReadingBlendCascade LambdaRankMarket devig
Own history0.10%0.04%0.10%–

Result rows are joined to the boards by FirstCycling rider id through the riders table. 0 row(s) needed the normalised-name fallback; 1 finisher(s) could not be matched at all.