Race 1 · Chelmsford Citypool vs model · Thu 5 Nov 2026

pool sharemodeledge, pts

10LABICHE (GB)-4.631% · 36%
1JENSON BENSON (IRE)-2.218% · 20%
6CELTIC SPIRIT (GB)-2.311% · 13%
7FAR FAR OUT (IRE)-0.18% · 8%
4MUY MUY LOCO (IRE)+0.76% · 5%
5GIFTS DIFFERING (GB)+1.56% · 4%
14ECHO THAT (GB)+3.74% · 0%

Result pending · record

British racing picks — Fri 6 Nov 2026

Free horse racing picks for today's British cards: tote pool share plus sixteen form layers measured on 2,226 races, for every British track carried on the Turkish tote. Our ranks are written before the first race and scored after it: the record.

Unproven model — read this first

In a walk-forward test on 1,626 races the combined model did not beat the tote pool (-0.2 points on top-3 coverage). The ranks below are published as an open experiment: each one is written before the race and scored on the record, with the pool favourite as the benchmark to beat.

No British card up yet

TJK publishes foreign cards the evening before. Until then, browse the archive.

What the numbers mean

Pool share and edge

The Turkish tote (TJK) takes bets on British racing; each runner's share of that win pool is the market's opinion, published before the off. The model starts from that share and adjusts it with sixteen form layers (trainer, jockey, sire, damsire, owner, last finish, form, days since, head-to-head, track record, draw, rating, weight, age, depth of history). Edge is the model probability minus the pool-implied probability, in points. A positive edge means the model likes the horse more than the crowd does.

How the model was tested

Weights were fitted by conditional logit on 2,226 British races and tested walk-forward: each block scored with weights fitted only on earlier races, 1,626 races out of sample. On its own the model does not beat the pool (-13.5 pts top-3); combined with it, top-3 coverage moves -0.2 pts and likelihood improves. Verdict: failed. The gain is calibration, not coverage: the record page shows exactly how it performs.

Layer weights: piyasa +0.83 · form3 +0.25 · adres -0.23 · antrenor +0.22 · son_bitis -0.18 · jokey +0.16 · aygir +0.14 · siklet +0.08 · damsire +0.08 · kgs -0.04 · h2h -0.04 · sahip +0.03 · draw +0.02 · hp -0.02 · n_gecmis +0.01 · yas +0.00 · son_fark +0.00

Usable, thin, blind

A race is usable when at least 70% of runners have British form on file and the field averages two or more runs; thin at 40%; otherwise blind, where no verdict is given and the order shown is the market's. Before the pool opens (TJK opens it on race morning) every race is blind.