Ever seen the movie Moneyball? Watching this movie changed the way I look at sports. Before, I thought sports and my IT focused education were strictly separated. But is seems quite the contrary: the movie describes the switch between measuring player performance traditionally, dominated by anecdote and intuition to an evidence-based approach. Nowadays, it is possible to record the exact movements of players in team games such as football, basketball and baseball. This science is driven by the relatively new ability to gather vast amounts of data about the players and the play while the game is in progress, resulting in a totally reformed sports environment.
However, in many of these sports, the capacity to gather data has not been matched by an ability to process it in meaningful ways. So an interesting question is what challenges sports sciences face in crunching this data effectively. What are the open questions in this rapidly evolving field?
The big challenge in sports science is to use this data to gain a competitive advantage, whether in real time during the game or to help in training, preparation, or recruitment. But while researchers have made significant progress, there are also important hurdles barring the way.
First off, the older generation have a hard time accepting and integrating the new way of work, as also described in the movie. Another significant challenge involves understanding how players can dominate parts of the pitch near them. In sports science, a player’s dominant region is the region he or she can reach before any other player.
Another related challenge is to work out whether a player is open to receive a pass. That means determining if there is a certain speed and direction that the ball can be passed so that a given player can intercept it before any other.
But perfecting algorithms that can solve these problems is only half the battle. The next stage will be to ask how these tools can help improve performance both on and off the field. Can they be used as a metric of player performance and value? Can they determine whether a player who is successful on one team will be also be successful on another? And can they work in real time during a game to help coaches and fans alike? I am really curious what the future will bring.
Challenges of Big Data in Sports.
12
October
2016
Hi Ronald!
Interesting post to read, since I am also interested in big data in sports. I think coaches can benefit from this data real time, just like we see with field hockey these days. The coaches track the heartbeat and the amount of lactic acid in the muscles of a player. I think in the future everything will be based on big data in sports, but we should be aware to not only judge players on their statistics.
Gr,
Tim
Hi Roland,
First of, very interesting post! As a basketbal fan, more and more statistical analyses seem to pop up. I’m also certain it can estimate a players value with a high degree of certainty. The first problem you name is only a matter of time before this becomes irrelevant as the athletes are mostly young this will not take long. The second problem isn’t as much a analical one but rather a coaches dillema. Getting the right guy on the right position at the right time will always remain something the athlete as to accomplish in the given system. But making the perfect pass is still something the players have to do, no machine can help with that.
Gr, Peter
Nice and also very interesting article! As a big sports fan i actually had the same thoughts about IT and sports as two seperated things. However, i do think that IT is playing a very big and also very important role in the sports business nowadays. Using all the statistics per game for example, it is possible to bring almost everything in card about the sport.
By looking at football, almost every team in the big competitions are using data to analyze their opponents or to analyze their own players. I also do believe that teams nowadays selecting players mainly on data.
Using data in sports is absolutely a way to gain a competitive advantage!