About KayLoL

Last updated 2 September 2026

Why the numbers here look lower than everyone else’s

This is the thing worth understanding before you judge the tool, because it is the one place KayLoL deliberately makes itself look worse.

A draft-prediction model can be evaluated two ways. The easy way is a random split: shuffle all your games, train on most, test on the rest. The hard way is a held-out patch: train only on games that happened before a patch, then test on the patch itself — the way the model will actually be used, on a meta it has never seen.

Random splits produce better-looking numbers, because the test games sit in the same meta as the training games and some of the answer leaks across. Filtering to only the highest division, or discarding games that ended early, flatters them further. KayLoL is measured the hard way, on a whole unseen patch, across the whole ladder. That costs several points of headline accuracy and it is the honest number.

It also means the number to compare is not the one most sites lead with. Does it work? publishes three separate layers of evidence, ordered by how hard each is to fake, and never merges them into a single figure — including predictions this API returned before the games were played, which cannot be reconstructed after the fact.

Calibration over discrimination

Most tools optimise for telling winners from losers. KayLoL also cares whether 57% actually means 57% — that across every draft it called at 57%, blue really does win about 57 of 100. A model can rank drafts well and still be badly calibrated, and a confidently wrong probability is worse than a hedged one when you are using it to make a pick.

That is why the metrics page leads with a calibration curve rather than an accuracy score, and why the site keeps saying the same uncomfortable thing: a draft is a small part of a game. Expect probabilities near 50%, and read the direction rather than the last decimal.

Where the data comes from

Completed ranked games collected from Riot's public Match API — the same games Riot already publishes to any client, and the same source every match-history site is built on. They are used in aggregate, to train the model and compute the champion statistics behind the tier list.

Nothing here exposes an individual player's match history, and no page will tell you anything about a player other than the visitor who typed their own name in. What is stored, what is deliberately never stored, and how to have it deleted are all in the Privacy Policy.

What it is not

• Not a guarantee. It is an estimate from historical games, not a prediction about yours. See the Terms of Service.
• Not affiliated with Riot Games. The notice at the bottom of every page is not boilerplate — this is an independent project.
• Not a business. No ads, no subscriptions, no data for sale. It can go offline or change without notice, and nothing should be read as a promise it will not.

Contact

Bug reports, corrections, and questions about the method are all welcome at contact@kaylol.gg. If you think a number on this site is wrong, that is the most useful message you can send — the whole argument of the metrics page is that the claims should be checkable.