One horse. One bet. Every day. Sly Man’s read on the day’s card — the shortlist, the price, and the case for the pick.
Browse the logbookThree fillies' novices, a couple of novice hurdles, and a pair of steeplechases — Halloween throws a mixed card, and the model kept its head while the fields got small and the form books stayed thin. The pipeline started with every declared runner and worked through four sequential filters: odds band 2.0–50.0 decimal (no odds-on, nothing wilder than 49/1), field size 6–14 runners (small enough to be readable, large enough to mean something), and finally a lay-of-day collision check that removed 1 runner flagged by the opposing book. Feature weights going into the composite were: market_move 1.6, speed 1.5, form 1.2, class_change 1.0, trainer_strike 0.8, going 0.8, draw 0.5 — with market movement carrying the heaviest hand today, given how thin the form data is across the shortlist.
The day opened with 46 races declared and 455 runners. The odds filter trimmed that to 400, the field-size filter to 284, and the lay-of-day removal brought the live pool to 283 runners. From those, the engine ranked by weighted composite and handed me six names worth a proper look.
Five horses separated themselves clearly from the pack. So This Is Love sits top of the scoring with a composite of 7.65/10 — the SR figure of 152, a z-score of +1.59 on speed, and a maximum market-move score off a clean steaming move are the main drivers. Merveilleux Rousse scores 7.48/10 and carries the widest model-vs-market edge on the card at +279%, with Owen Burrows posting a blistering 32% strike rate over the last 30 days — she's the value play published separately. Bondy Boy comes in at 7.44/10, King Kubala at 7.31/10, and Cavalier du Luy at 6.87/10. The scores at the top are compressed: the gap between first and third is only 0.21 — well inside the 0.4 threshold that would count as a clear lead. When the model cannot separate them, the tie-break rule is the shortest price on the shortlist, on the logic that the market's collective read is the best available signal. That is Bondy Boy at 2/1.
The read I keep coming back to is the market. Bondy Boy has been steamered — a strict majority of bookmakers shortened their price, and not one drifted — which generates the maximum +2.00 market_move contribution and accounts for the bulk of his 7.44/10 composite. That market signal is carrying weight 1.6 in the engine, the heaviest of any feature, and it is there precisely because it tends to aggregate information the model cannot otherwise access: stable whispers, workout times, jockey confidence, ante-post money. When a horse this short gets that kind of uniform support, something is being communicated. Speed backs the case too: an SR of 152 against a field mean of 121.0 gives a z-score of +1.22, weighted at 1.5 — that is a solid speed advantage in a Class 5 maiden over 6f16y at Southwell on Good going. Geoff Oldroyd is running at 22% strike rate (2/9) over the past 30 days, which is a hot spell for a yard of that size. The trainer-strike contribution is modest at +0.85, but it points in the right direction.
The gaps matter here. Form is UNAVAILABLE — there is no race-by-race string to lean on, so I cannot confirm this horse has shown its speed figure in a competitive context rather than a quiet gallop. Going data is also absent: no career runs on Good recorded, so if conditions soften further through the day at Southwell, there is no evidence either way for how Bondy Boy handles it. The market-move score is doing heavy lifting, and markets are occasionally wrong — particularly in maiden company where information is scarce and layers can move prices for non-performance reasons. The model-vs-market edge is only +13.1%, the narrowest on the shortlist by some distance, which means the price does not offer much cover if the read is wrong. And So This Is Love is sitting there with a higher composite (7.65/10) and the same maximum market-move score — readers who prefer to follow the top-scoring model output rather than the tie-break rule have a legitimate alternative. I have written the bet as the engine called it.
Bondy Boy · 2/1 · 1 unit · MEDIUM
The Fox’s Wire · Bet of the Day
The algorithm pulled five contenders from today’s card. One earned the ticket — the rest are what it beat. When each race settles, the finishes fill in so you can judge the shortlist, not just the selection.
Position only — payout-neutral. A process check, not a P/L. Click any horse to read its profile.
Value pick 4 of 24 won · +6.83 units at advised prices · since 11 October 2026. Kept separate from the bet’s record above.
