Naive Model Benchmarks
How Good Can We Get With A Simple Model?
The first naïve model that was tried was very simple: in every game, the home team was predicted to win, with a likelihood of 1, by a score 5 points (the home advantage). This gave us a rough idea of how our elo scores predicted match results, but was almost entirely arbitrary. This gives a lot of room f...
First Model Check
There are a lot of moving parts in an elo calculation. For each match, we have as elo score for each team (elot) that is calculated using elo scores for each of the players (eloi) on the teamsheet. The exact computation of this team score will be changed later, but currently its a contribution system, with each player contributing to the team’s ...
19 post articles, 3 pages.