:format(webp)/cdn.vox-cdn.com/uploads/chorus_image/image/50267017/Ziggs_1.0.jpg)
We’ve all been there before — you queue up for ARAM, and get handed Evelynn, Rek’Sai or some other champion that is either A) not very good for ARAM or B) not very good for you. Meanwhile, the other team has Soraka, Nidalee and Jayce, and it feels like the game is over before it actually began.
Well, is it? Thanks to a new tool on Manaless, you can find out your chances at winning an ARAM game pretty accurately just by the champions from the two teams.
With such discrepancy in power between different champions and the fact that the champions chosen in ARAM are random, it is natural to ask how much of the game is decided as soon as the champions are selected. In other words, given the champions locked in for both sides and no other additional information, how well can we predict the outcome of the game?
By constructing a predictive model using machine learning techniques, I have discovered that I can predict the outcome of ARAM games in Patch 6.15 with around 66% accuracy.
The tool also has a randomize feature — we used it and, for example, a team with Cassiopeia, Teemo, Azir, Udyr and Sion would have between a 48-52 percent chance to beat a team with Singed, Karma, Mordekaiser, Miss Fortune and Renekton (a pretty even matchup!).
According to the site, the champions with the lowest ARAM win rates on Patch 6.15 are Ryze, Evelynn, LeBlanc, Rek’Sai and Kha’Zix. The five highest are Ziggs, Sona, Galio, Teemo and Swain -- all above 61 percent.
If those two teams matched up, the latter would have a greater than 70 percent chance of winning. But don’t lose hope! Even if team comps are lopsided, League games often come down to champion comfortability and decision-making, especially at lower elos. So keep your head on straight and grab some IP!