Racing tips,
proven by data.

A machine-learning model trained on 38 years of racing — 3.8 million runners across more than 400,000 races — rates every runner each morning. No tipsters, no gut feel. The model speaks, we publish.

3.8M
Runners analysed
400k+
Races in the model
38
Years of form
3
Regions: UK · IRE · HK

The dataset behind every selection — 1988 to today, refreshed daily

Registered before the off Graded against the result Led by CLV, not winners Cancel anytime · 18+
See it in action

The model's work, in your account

Every morning you get the tiered card, the model's read of every runner, and a record that builds in public. Click through a preview of the member experience.

app.algohorse.com/accountIllustrative preview
NAP OF THE DAY
Stardom Glory
Chester · 1:50 · GB Place
70%
MODEL · TO PLACE · registered 2.50
2:25Next BestFurturraYork · GB66%3.40
3:05Next BestGiant SequoiaCurragh · IRE61%4.00
3:40SpecNever So BraveYork · GB58%5.50
Every selection registered before the off & graded against the result.Open a free account
How it works

A model, not a man with a tip

No insider whispers, no gut feel. Every selection comes from a machine-learning model trained on decades of form, graded the same way every day.

01 / DATA

Decades of racing

38 years of results, form, ratings, going, draw and connections — refreshed daily across three jurisdictions.

02 / MODEL

Probabilities, scored

A gradient-boosted model rates each runner's chance of placing. No cherry-picking — the model speaks, we publish.

03 / PROOF

Registered & graded

Every tip is logged at the price available, before the off, and graded against the result — so as our record builds, we can publish it in full.

See the full methodology →

The data

Four decades of racing, in one model

Most tipsters sell a hunch. We built a machine that has studied more racing than any person could in a lifetime — and reads every card the same way, every day.

The dataset

3.8M
runner records
400k+
races
38
years (1988–today)
3
jurisdictions

Form, ratings, going, draw, class, connections and prices — cleaned, joined and refreshed daily across UK, Irish and Hong Kong racing.

How the model thinks

LearnGradient-boosted win & place models on 38 years of results
CalibrateProbabilities calibrated so a "70%" really means 70%
ValidateWalk-forward tested on unseen seasons, strict leakage controls
PublishEach morning's tips registered at the price available, pre-off
Built and validated like a quant model — not a tipping column

The number we'll lead with: CLV

Closing-line value measures whether the price we flagged beat the market's final price — the single hardest metric to fake and the best long-run signal that a process has genuine information. Every tip is registered before the off and graded automatically, so as our public record builds, we'll show it in full: strike rate, return and CLV, by tier and region. We'd rather earn that page than fake it. Why CLV →

What you get

The model's card, every morning

A tiered daily card — NAP, Next Best and Speculative — with the model's confidence and the registered price on every pick, delivered to the app, email and Telegram.

NAP OF THE DAY
Stardom Glory
Chester · 2:02 · Place · GB
PLACE PROBABILITY
70%
PRICE (registered)
2.50
FIELD
6
Furturra · York · EW66%
Giant Sequoia · Curragh · Place61%
Never So Brave · York · Place64%
Algohorse · Telegram
Morning card is live — 12 selections across UK, IRE & HK. NAP: Stardom Glory (Chester 2:02), registered at 2.50. Full card & reasons in the app. 18+ · bet responsibly.
Delivered every morning to app, email & Telegram
EVERY TIP, REGISTERED & GRADED
Logged before the off
Settled against the result
Beat-the-SP (CLV) tracked
The difference

A model, held to a higher standard

The tipping industry runs on selective memory. We run on a process you can audit.

Algohorse
Typical tipster
Selections from
A model on 38 years of data
One person's opinion
Tips registered before the off
Often not
Losing weeks shown in full
Quietly deleted
Leads with CLV
Cherry-picked winners
Figures with sample size & CIs
Screenshots
“Guaranteed profit” claims
Never
Common
Pricing

Start free. Upgrade when the model convinces you.

No guarantees, no "quit your job" nonsense. Just transparent, model-driven tips and an honest process — cancel anytime.

Save ~28% annually
Free
£0
THE MODEL, OPEN TO ALL
  • One model tip per day (on delay)
  • The methodology, in full
  • Data studies & insights blog
Create free account
Pro
£79/mo
RUN IT LIKE A DESK
  • Everything in Core
  • Value alerts — where the model beats the market
  • Bet tracker — your real P&L, ROI & CLV
  • Staking calculator (Kelly) + earliest delivery
  • API access & full data export

Compare plans in detail →

FAQ

The honest answers

Will I definitely make money?

No — and anyone promising that is lying. Betting carries risk and variance. What we promise is transparency: a model-driven process, with every tip registered and graded so that — as our record builds — you can judge the edge for yourself.

What is CLV and why do you talk about it?

Closing Line Value measures whether the price we advised beat the market's final price. It's the single hardest metric to fake and the best long-run indicator that a selection process has genuine information — which is why it's central to how we'll report our record as it builds.

How are the tips produced?

A machine-learning model rates every runner each morning from decades of data — no tipsters, no opinions. Selections are registered before the off and graded against the result automatically.

Can I cancel anytime?

Yes. Monthly or annual, cancel whenever — no lock-in, no 'money-back guarantee' gimmicks.

Free insights

Data studies, straight to your inbox

What 38 years of racing actually tells us — CLV, biases, value. No spam, unsubscribe anytime.