Harrison Afful

Machine Learning the Crew by Eliot McKinley

Machine learning is so hot right now and if Skynet is going to destroy all humans, it should at least know a little bit about Major League Soccer’s Columbus Crew. To wit, I created a machine learning model to classify which position in a Gregg Berhalter 4-2-3-1 formation a player most likely played in during a single game.

I chose the Crew for a couple reasons. First, they are my favorite team. Second, they had consistent coaching for a long period of time with a defined style of play. The latter is very important, as the model has to be trained well in order for the results to make sense. Since the Crew almost always played a 4-2-3-1 that relied on ball possession to disorganize the defense and create goal opportunities (get used to that phrase USMNT fans) it was a perfect test of whether this kind of thing could be done.

Read More

Columbus Crew SC 2017 Season Preview by Kevin Minkus

By most accounts, the 2015 MLS Cup runners-up had a pretty poor 2016. A team that was generally expected to contend for a Supporters’ Shield and a championship finished the season 9th in the East on 36 points. During a stretch to start the year that saw them win just two games in 11, they jettisoned their Best XI forward, Kei Kamara, for feuding with their best chance creator, Federico Higuain. Higuain then sat out 14 games throughout the rest of the season with injury issues stemming from a sports hernia.

In spite of this turmoil on offense, the team’s real problems were on the other end of the field. The Crew gave up three or more goals 11 times, and their 58 total goals allowed was second worst in the league, though they were only fifth worst in expected goals allowed. The fact that Columbus is a possession oriented team means that they generally surrender few shots- in 2016, they allowed only about 12 shots per game. But the shots they did give up tended to be higher quality chances.

Ola-tta more after the jump.

Read More