Soccer predictions API: title, top-four and relegation odds

A season simulator for soccer leagues. It takes the live table and the real remaining fixture list, plays the rest of the season thousands of times, and returns the probability of each club winning the league, finishing in the qualification places, reaching a playoff or going down.

Open on Apify API reference Input schema

What it returns

How the model works

Each club's strength blends its current-season form from the live standings with a baseline built from previous seasons, so a club three matches into the season is not judged on three matches alone. A home advantage is applied to every simulated fixture.

In each simulated season the strengths are redrawn from a distribution rather than fixed, which keeps the output from becoming overconfident. Every remaining fixture is then resolved from the strength gap between the two clubs, the final table is built, and the league's own rules decide who finished where.

Those rules differ a lot between competitions. The simulator knows the number of qualification and relegation places per league, playoff formats and split tables, and it can run several leagues in one job.

Leagues covered

16 leagues from ESPN's public feeds, including the Premier League, Championship, LaLiga, Serie A, Bundesliga, Ligue 1, Eredivisie, Primeira Liga, Super Lig, Brasileirao, Liga MX and MLS. Several leagues can be simulated in the same run.

16 ready-made examples

Each one is a saved configuration with its input filled in. Open it on Apify and run it in one click.

Common questions

Why can a club high in the table have a low title probability?

Because the table only records what has already happened. The simulation also weighs how strong each club is and who it still has to play. Early in a season, two clubs on the same points can be tens of percentage points apart in title or relegation probability.

How is this different from a match prediction model?

This model answers season questions: who wins the league, who goes down. It resolves each simulated match from the strength gap, which is right for a season but too coarse to price one specific fixture. For single matches there is a separate Dixon-Coles model, listed below.

Can I compare the output with bookmaker odds?

Yes. Pass implied probabilities for the markets you care about and each row comes back with the model probability, the market probability and the edge between them.

How often should I run it?

After each matchday is enough for a season forecast. A daily schedule on Apify also works and gives you a history of how the probabilities moved, which cannot be rebuilt later.

Other models