Analytics is a hot topic in sports today. Pro teams and leagues are on the look out for new ways to use analytics for a plethora of decision making instances — from improving the fan experience and building sponsorships to making better draft picks and predicting injuries.
Everyone recalls the Moneyball story about how the Oakland A’s used analytics to create a winning team for the 2002 season. For many, that story was an eye-opener on the power analytics had on player selection. But a lot has changed since then. Today, teams are turning to analytics to answer tougher problems and mine unprecedented mountains of data. Here is a quick look at a few of the roles analytics plays in sports both off and on the field.
Getting closer to fans and building sponsorships
Fan loyalty is everything in the sports business. The more a team knows about its fans, the better it can connect with them and build loyalty. Sports teams today are using analytics to dig deeper into fan preferences and behaviors, so they can target their marketing efforts with laser precision.
Consider Major League Soccer (MLS), the top pro-flight soccer league in the US and Canada. MLS has been creating a data warehouse, merging fan data from all 19 of its soccer clubs and its many CRM and ticketing systems. Now MLS is using analytics on that data to get to know its millions of fans and create personalized campaigns to increase ticket and merchandise sales and build lifetime loyalty.
Segmentation also plays a role in sports. By combining variables, such as game attendance, purchase of team merchandise and attendance at season events, teams are grouping fans based how likely or unlikely they are to renew season tickets. By targeting ‘fence sitters’ with personalized content, they are able to increase retention rates. Further, teams can analyze how often fans click on emails to fine-tune approaches. Some teams are even beginning to use analytics to mine unstructured data on social media sites.
Professional teams and venues are looking for ways to use their fan data to engage during events. Many venues already have iBeacons and Geofence technologies in-place. By combining knowledge of fan preferences and behaviors with geo-location and predictive analytics, teams can deliver the targeted content to fans in real-time during an event.
Sponsorship is another main source of revenue for sports teams and leagues. Sports teams are looking for new ways to use fan information to build a better story for their partners on why they should invest. Analytics is beginning to play an integral role in building that story.
Better draft choices, unique training schedules and injury prevention
Like in the Moneyball story, analytics has the ability to play a key role in making smarter, better draft picks. But analytics also plays role in optimizing player training. Teams pay big money for players, so the last thing they want is for a player to get injured on the field.
What’s changed since Moneyball is today, teams are collecting massive amounts of player performance data — more data than they know what to do with.
Soccer teams in Europe are putting wearable technology on players to track speed, location, distance run and even collect biometric data, such as heart rate and temperature. Since the 2013 season, all MLS teams in the US started to use the Adidas miCoach Elite system for data collection.
In pro-basketball and baseball, where unions are against wearable devices, the focus is on viewable data. If you go to an NBA game and look up, you are likely to spot six SportVU cameras in the rafters.
At this point, the teams are still looking for novel ways to use the thousands of data points they collect during each game. This is where analytics comes in.
In addition to helping teams develop unique training schedules for players, analytics is also being used to predict when players become susceptible to injury. By combining data collected on the field with variables like fatigue, stress, sleep, training intensity and nutrition, teams are starting to uncover hidden trends that cause injury. Many experts believe this to be the future of advanced sport analytics.
Entering a new realm in sports
But even with technology advances, analytics in sports still faces challenges. A lot of teams do not have the internal resources for putting analytics to work. Most of the money in sports goes to player salaries. What’s more, when it comes to draft picks, a lot of managers and coaches who grew up in the game still prefer to rely on gut instincts for decision making. That’s what the Moneyball story was about, the new school of analytics versus the old way of making draft picks.
But it’s clear the sports culture is shifting. Analytics is already beginning to play a much bigger role, especially as teams search for innovative ways to use the huge amounts of on-field data they are stockpiling.
© 2015 Sport Techie | This article was written by Jim Tobin and first appeared in the Sport Techie on June 12, 2015.