We did, it helps quite a lot! Concerning the model, we use Gaussian process classification with a logit link function, a linear kernel and Expectation Propagation as inference method.
3 karma · joined June 9, 2016
Concerning the predictions, they depend on the starting 11 for each team. We took the most recent ones, i.e. during the last friendlies, which are probably not the ones that will actually start the game!