Using Machine Learning to Predict Current Ability

We will now use the model to predict the CA of some players in the game. The first player is Ridle Baku. He is a fairly standout player in the game in that he can play in many different positions. This essentially inflates his in-game CA compared to what it would be if he could only play right-back.



His recommended CA in the test save is 152 whereas the ML model predicts a CA of 151. Very accurate!



The next player is Kevin De Bruyne. He too can play multiple positions, has a strong weaker foot and is one of the 'outliers' at the top-end of the current ability range.



His recommended CA in the test save is 186. The ML model predicted a CA of 180. Not bad for such an outlier!