FIFA ranking: Evaluation and path forward

In this work, we study the ranking algorithm used by Fédération Internationale de Football Association (FIFA); analyze parameters that it currently uses, show formal probabilistic model from which can be derived, and optimize latter. particular, analyzing games since introduction of in 2018, conclude game’s “importance” (defined FIFA algorithm) is counterproductive point view predictive capacity algorithm. We also postulate should rooted modeling principle, where Davidson proposed 1970 seems to an excellent candidate, preserving form used. The results indicate considerably improved using home-field advantage (HFA), as well explicit for draws game. Moderate but notable improvement may achieved introducing weighting with goal differential, which, although not a compatible current tuned characteristics football competition.