Analytics is vastly redefining sports, with teams repeatedly signing and scouting players based on insights from the ‘stat-geeks.’ It has seen teams, players and athletes conquer previously unscalable heights and adopt different styles, techniques and methods that have aided in vastly superior performances. For example:

  • The NBA’s Houston Rockets signed three players -- James Harden, Jeremy Lin and Omer Asik -allowing the team to shift to a free offensive style. The team is now among the NBA leaders in attempting shots from both the three-point range and very close to the hoop — both logical places to shoot from, according to the numbers.
  • In the 2014 FIFA World Cup, the winning German team leveraged SAP software and employed several data-driven practices to optimize their performance.
  • Rugby coaches are now using predictive analytics to assess the likelihood of player injury, using this insight to deliver personalized training and nutrition programs for players at risk.

In an industry where milliseconds and singular movement variations can spell the difference between jubilation and heartbreak, the margin for error is simply non-existent and hence the growing adoption of emerging modern day heavyweight: analytics. If the Oakland A’s Billy Beane, of Moneyball fame, taught us anything, it’s that the game can be won or lost before it even begins.

Why Sports Analytics?

Analytics has become an integral part of the sporting world, be it FIFA, NBA or NHL, with large volumes of data generated through each practice and game, both structured and unstructured. MIT Sloan Sports Analytics Conference is a testament to the emphasis and interest placed on sports analytics.

Heat-mapping techniques are being used to track the movement of players in team games to understand which spaces remains to be exploited and the areas in which passes were lacking or were weak. Introduction of vital monitors tracks players’ overall fitness providing an understanding into the assets and drawbacks of each player. Techniques such as movement analysis, game video and location sensors combined with online scouting reports have enabled coaching staff to slice and dice individual components of sports performance.

Thus, we see a shift in the conservative paradigm with some management staff relying more heavily on analytics than others. However, the underlying competition in sport and the rapid movement of coaches and managers between teams has facilitated a viral transmission of analytics ideas across leagues and teams. This has resulted in tailored, proprietary and ‘better’ analytical initiatives.

The Challenges

The greatest problem is breaking from traditional practices and mindset and it has been summarized beautifully by head of analytics for an NFL team:

‘I am working against a culture of indifference toward analytics. Despite that, I am trying to find the one or two things the coaches will use. Every time I engage them—and that’s a struggle in itself--I throw out several things. If they accept one, I consider myself successful. Football is a good-old-boy culture that sees security in the status quo, and it has been hard for analytics to make a dent in it.’

Another hurdle that undermines the progress of analytics in sports: professional teams and sports are businesses. The average professional sports team has a lower market value than the last company on the Fortune 500 list. Therefore it is rare for sports teams, even the richer ones, to accommodate large analytical teams.

However, wouldn’t most team managers love to add analytics to the mix of nutrition, fitness and training in order to hit the ball out of the park?

The Future

The way to operationalize any sports analytics initiative would be to follow the below steps:

  1. Data Engineering Layer – The first and critical step is to ensure there’s integration of all the available data (both internal and external) into a common database since incomplete data will yield non-optimized results/analysis.
  2. Structured Problem Solving Platform - While most analytics products focus on complex analytical techniques and quantitative methods, getting business problem definition, analytical design and data selection right heavily influences the efficiency and efficacy of all downstream tasks along the analytics value chain.
  3. Intelligent Systems – Easily implementable and scalable operational intelligent system platform in place capable of both real time as well as batch analytics through a life cycle paradigm including data capture, data processing and deployment of analytical tasks to help generate consumable business insights for consumption.
  4. Consumption of Analytics – Many organizations fail at this step. Creation and consumption of analytics has to go hand in hand in order to reap the holistic benefits of any analytics initiative. Two aspects need to be taken care of: identifying what information is actually helpful and who would benefit from it.

Sporting perfection may indeed never be reached. But as technology moves to shape our world, the margin between the present and perfect will soon become inconsequential.  In an industry that understands only one thing – winning-- analytics may just be the perfect coach.
Sumit Prasad is a manager at Mu Sigma, a decision sciences and big data analytics company helping enterprises institutionalize data-driven decision making. 

Register or login for access to this item and much more

All Information Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access