$Assess team win rate by combining individual win rates?$

Question

$Assess team win rate by combining individual win rates?$

Suppose I have 5 players on each team in a game where each player selects a character (League of legends, Valorant, etc.).

I am considering the overall win rates of the characters, and the unique win rate attached to the player is not considered (i.e some players focus on using X character, so their win rate may be higher with this specific character, I am ignoring this, I am using the win rate of a character across all games played in a given season).

Each character has been played (in a game that has matches consisting of 2 teams formed by 5 players each, selected at random) anywhere from at least 4,000 to even 60,000 times in a given patch (lets just use season for simplicity).

Upon entry, team A may have overall individual character win rates (calculated across all matches played from and up to a certain point) of [40%, 50%, 55%, 50%, 60%] and team B may have individual win rates of [50%, 45%, 60%, 40%, 65%] for each character (not player) respectively.

Is it naïve to just average the win rates and consider that the team win rate, or is there a more robust method of doing this?

Despite all the characters having 4000+ games, some may have only around 4000, some may have 8000, some may have even more depending on popularity, so I imagine there may need to be sort of weighting, but I am not sure if 4000+ games is enough to disregard the need for a weighting system (as opposed to a basketball player playing less than 20 games a season and then 70 games the next, clearly weighting there may be more important).

My goal is to determine a predicted win rate for each team given the win rates of each character selected.

I can come up with everything, I am just trying to figure out that last key data point (predicted team win rate), it seems almost too easy to just average the 5 win rates, or maybe I am just overthinking it =)

Thanks!

Statistics Probability

Jetset

8

Report

Daniel90

0

This is not my area of expertise, but your bounty seems a bit low.
Jetset

0

Increased it.

Answer

The answer is accepted.

Join Matchmaticians Affiliate Marketing Program to earn up to a 50% commission on every question that your affiliated users ask or answer.

Daniel90

0

This is not my area of expertise, but your bounty seems a bit low.

Answer 1

Answers can only be viewed under the following conditions:

The questioner was satisfied with and accepted the answer, or
The answer was evaluated as being 100% correct by the judge.

View the answer

Hi! I come from Dota 2 and I have over 12.000 hours of playtime over almost a decade of playing. I also have a background in Statistics, Economics and Mathematics.

I'm afraid I disagree with the idea of averaging the individual winrates. To give you an example, typically there are roles in competitive games, like that of Support, Carry, Jungle, ADC or whatever. One would agree that a team where 5 of characters have the same role (say, all ADC) would generally do bad, even if the individual characters happen to have good winrates individually.

To get an accurate assessment of a teamlikelihood to win (winrate) based on the composition of the team, one should take into account the role of the characters and even the skill bracket of the game. For example, a team with 4 carries might be subpar in an highly skilled game of Dota 2, but in a low level game it might not do so bad in raw numbers. This is why many characters and items have different winrates across different skill brackets.

To provide a solution, I suggest training a classification model (say, a random forest), that will take into account all available information on team composition: character roles (which might have to be manually input, as the meta changes), skill bracket, individual win rate of characters and every other information that it is available (for example, different regions tend to see different 'metas' and winrates for specific characters). Based on this information, one would try to predict the probability of winning (using on all available games played by such combination of features).

To my knowledge, this would be the most useful approach to try and predict winrates for a team composition. The choice of a classification model will be critical, so perhaps an xgboost or a neural network might do better and you can select the best model using cross validation, for example.

Mathe

3.3K

$Assess team win rate by combining individual win rates?$

Answer

Related Questions

Search