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.
What goes into a rating
| Form | recent runs, finishing positions, beaten lengths |
| Class & ratings | official ratings, race class, weight carried |
| Conditions | going, distance, course, draw bias |
| Connections | trainer & jockey form, recent strike patterns |
| Market | prices & movement, used to measure CLV — never as hindsight |
No post-race information ever enters a feature
Data is the moat
Anyone can post a tip. Almost no one can read 38 years of racing consistently and prove it. The dataset — and the discipline of grading every selection against the result — is what separates Algohorse from a tipping column. As that graded record builds, it becomes the proof. Why we lead with CLV →
Start free. Upgrade when the model convinces you.
One model tip a day, free — the full daily card across UK, IRE & HK on Core.