Predictive Analytics in The beautiful game(Soccer)

What is the beautiful game? It translates from ‘O Jogo Bonito’ , a Portuguese phrase, made famous by Pele, a Brazilian footballer, that has been iconized in history because of the game of soccer.

As a big soccer fan, I know the right terminology is football in the rest of the world except North America, for the sake of clarity, I chose to call it soccer in the write up, I hope can find it in your hearts to forgive me and not get caught up in semantics.

Now that is out of the way, I’ve been an avid soccer fan since before I knew how to walk (trust me bro..) it was like a rite of passage from father to child. I played as a kid all through high school, college and till this day!!!

Now training to be a Data scientist, I’ve been curious to know what the science has to say about the beautiful game. Honestly, I hardly ever need a reason to talk about soccer and/or mixed martial arts (saving that for a different blog). Notwithstanding I began the research with an hypothesis “The Beautiful game cannot be modeled to predict results accurately”

“Sports analytics is the process that identifies and acquires the knowledge and insight about potential players’ performances based on the use of a variety of data sources such as game data and individual player performance data. These advanced and sophisticated types of analytics should be able to extract valuable actionable insights for the coaches and managers to utilize” Masoud Nikravesh.

To be specific, soccer analytics is the art of creating meaningful insights and decisions that can be acted upon using soccer related data. The data can be anything ranging from how many goals a team has scored to multiple factors like, how much distance a single player in a team has covered, or how many passes he has played and how many out of those were misplaced, how many out of those created chances for the team to score etc. In soccer, both predictive and descriptive analytics is used.

While predictive analytics predicts the possibility of an outcome, descriptive analytics analyzes the data in hand to come up with suggestions to increase the possibility even further.

Since most professional sports teams function as a business, sports analytics is a very useful tool in improving the business side. Soccer, the most widely followed sport in the world has also started adopting predictive analytics for the aforementioned reasons, however, the problem of soccer lies elsewhere. It has not been nearly as successful as other sports in predicting the performance of players or predicting the outcome of games

But when it comes to predicting an outcome of a game these predictive models have not been successful. This could be because of how dynamic a soccer game is, there are a lot of factors to consider, injuries in a game, red cards or yellow cards, and other factors that can’t be accounted for in the game.

From finding seemed to agree with my hypothesis, I believe there are intangible values like team spirit, heart, determination, desire, passion that I have grown to know to be the very essence of the beautiful game, that can’t be captured by the descriptive analytics, hence can’t be modeled in the predictive analysis. Which led me to wonder if this dynamism and intangibles are what make the game so passionate and beautiful. The very reason it brings the world together to enjoy the game.

Data collection, especially in soccer has increased multifold off late to capture various measures that have never been captured before. For example, Adidas have tied up with the Major League Soccer (MLS), in the US to have the players’ vitals and neurological reactions monitored with the help of a chip that will be inserted onto the players’ accessories like socks, jerseys etc. With the advent of such technologies, I believe it would lead to the development of new variables that have never been used in soccer analytics before. Maybe then more accurate predictive models can be for the outcome of a game can be generated.

Football can be exciting and it can be boring(I lied, it’s always exciting). It is unpredictable and polarizing. Often it is the cause of glorious celebrations, powerful enough to unite nations. But it can also be the cause of hooliganism and violence. Football frequently enters the realm of politics, and it also goes the other way around. Football is, unfortunately, often an instrument for financial corruption. I digress!

In conclusion, soccer is part of global culture. It is the biggest, most loved sport in the world and the phrase Beautiful Game suits it perfectly. In the game of soccer only one thing is guaranteed, Leo Messi & Cristiano Ronaldo would be involved with the goal or goals the game… ( sad to imagine them not playing). Apart from that there are too many unmeasurable variables at the moment or maybe predictive models are not a necessary addition to keep the game as beautiful as it is!