AI esports predictions, Without emotion, Based on data.

Ensitics is an esports prediction platform. Every day two models go through the tournament schedule across esports disciplines, such as Counter‑Strike 2, League of Legends, Dota 2, Valorant, Mobile Legends, Overwatch, Rocket League, Rainbow 6, Honor of Kings, and publish the matches where they see an edge: Confirm Value for results fast, about an hour before the match, and Value Spotter for planning ahead, in the morning and days before. A pick is two things: the side and a confidence level. Simple, easy to use.

What Ensitics isn’t: a stats database like HLTV or Liquipedia, and not a place where you can wager. You get the conclusion rather than the table you’d have to build it from.

2,208 of 3,061 graded picks have won since launch. It’s 72.1%, as of October 27, 2026. Everything is based on the historical database legacy (10+ years) mixed with the actual stats.

Two caveats worth having before that number means anything. First, the win rate is not profit: a feed of heavy favourites can win 80% of the time and still lose money. Second, it is a blended result of all our models — Confirm Value, Value Spotter and the previous High Confidence — and they behave very differently. Confirm Value keeps its own live record from Sep 24: Confirm Value stats.

CV is Confirm Value, for those who want results fast: a pick goes live about an hour before the match, once the market has moved toward the model’s side. Only picks at odds of 1.30 and higher are published — near‑certain favourites below that win often but add little.

VS is Value Spotter, for those who like to plan ahead: its picks come out in the morning and days before the match. It takes the opposite route — matches where our number and the bookmaker’s number disagree. These lose more often. They also produced all five of our biggest wins so far: O2 Blast at 6.20 (Overwatch, 5 June), Enterprise Esports at 5.30 (Valorant, 7 August), Super Club at 5.17 (Honor of Kings, 16 September), SYGaming at 4.72 (Honor of Kings, 24 June), Gen.G Esports at 4.29 (League of Legends, 27 July).

Mixing them without knowing which is which is the most common way to misread the feed.

Ensitics has a huge database of more than 13.3 million rows of data. This historical legacy makes the algorithm work.

The pipeline runs the same loop daily: scan every tournament across all the disciplines, pull the match‑level history for both teams (such as recent series, opponent quality, map and draft splits, roster state, event context), then keep only the matches that fit one of our two models: Confirm Value waits until the market confirms the side about an hour before the start, Value Spotter takes the matchups everyone else underrates, days ahead. Most matches don’t pass. On a typical day the models look at hundreds and publish about 15. Might be more, rarely less.

The output is deliberately narrow: a side and a confidence band. We don’t publish a probability for every fixture, because a number attached to a match we have no read on is worse than silence.

Yes. One pick a day, permanently, no card required to register. It’s the same model output as the paid feed, just less of it. The point is that you can grade us yourself for a month before spending anything.