If Soccer Is Getting More Predictable

A PAPER PUBLISHED AT THE END OF 2021 in Royal Society Open Science suggests your favorite professional soccer matches are not the nail-biters that they used to be.

- Sarah Wells

Researchers created a database of over 87,000 games spanning the course of 26 years in European soccer leagues between 1993 and 2019. For simplicity, they chose to eliminate tied games.

Factoring in things like strength of schedule, for each new match they used a logistic regression algorithm a classification algorithm that helps assign data into discrete buckets, like labeling emails as either spam or not spam-to predict the probability of their match's outcome. Researchers found a clear difference between the predictability of games played 10 years ago and matches played today. In a German league, for example, the model has an accuracy of 60 to 65 percent in the early 2000s, and 80 percent accuracy with data from the late 2010s.