Sports has always been a part of our lives. Whether it’s just watching a test cricket match on a lazy afternoon, or getting into an absolute frenzy during the Premier League finals. It has always been a part of who we are. We support teams representing our nation, or at times even nurture unconditional love for a team in another country. Despite sports, being with us since forever, the games have changed ever since the dawn of time. From the athletic attires to the gears, from matches being broadcasted on TV to matches being on internet livestream – the modality has been experiencing major changes throughout the years.
An amazing addition to this plethora of transformation is how athletes train themselves. From appointing multi-disciplinary coaches to using next-generation training gears – renowned athletes and top teams of the globe tend to leave no stones unturned when it comes to polishing their ‘diamonds’ to perfection. Every match counts these analyses so does every minute of the nerve-wracking training sessions. Athletes, regardless of the sports, have had a long-standing history of watching tapes of their previous matches. Usually, they or their coaches decipher the entire matches to small bits and pieces, from which they gather insights and then prepare a strategy based on which they are likely to perform in their next game. It’s a process much like the military – where precision and planning leads to victory. This meticulous part taking place at the backstage, i.e. the ‘planning and preparing phase’ has recently begun to witness a mass-scale innovation due to the help of Sports Analytics.
With the advent of technology, collecting massive sets of data is now easier than it has ever been before. Sports teams have started to appoint data analysts alongside their regular coaching staff to give their players an edge. These analysts collect every relevant data, analyse them and present the coaches with actionable insights – which is the ultimate tool that the coaches use to curate their game plan.
Yes, the entire realm of sports has now been invaded by a group of ‘lean, nerdy’ statisticians who are now working alongside their ‘polar opposites’ – a group of ‘tall, muscular’ athletes. Do you still think it’s a myth? Let’s take a look at some of the case studies below:
NBA – DATA LEADING TO DUNKS
NBA, the signature basketball franchise in the U.S. has been a pioneer in utilizing all the spectacular features that data analytics has to offer to their courts. The game of basketball in the U.S. has witnessed a steady rise in 3-point shots, and much has to be credited to data analysts figuring out this is what players should be focusing on to get the trophy. In fact, the former champions Golden State Warriors have the most established data analysts team in the entire franchise. As a result, other teams are following the same path. These analysts help teams to identify trends that may improve on-court tactics or practice drills. Moreover, the residues of analyzing large datasets enable the teams to identify their high-performing players as well as the low-performing ones; thus trading them off to other teams – a great case of attaining maximum efficiency and the team’s holistic ROI. The athletes themselves have started using wearables to trace their sleep and fatigue levels in an effort to avoid injury or mishaps.
The entire League itself has been very welcoming of using analytics to segment the overall state of the game. Hence, NBA even has started to organize an annual Hackathon, in a pursuit to recruit aspiring data analysts for the franchise teams.
USTA – TENNIS BECOMES MORE TACTICAL
Similar to NBA, another genre of sports have also successfully embraced the concept of analyzing data to attain peak performance. U.S. Tennis Association (USTA) has partnered up with IBM to come up with an analytics engine named Watson, to improve their tactics on court. Watson processes all the video footages captured during the matches and the training sessions. By analyzing all the videos, it uncovers certain insights that a player can easily use to his/her advantage, e.g. if a particular opponent favors cross-court shots early in a point but hits forehand shots down the line more often as a point progresses, a player can cleverly utilize this insight to position himself/herself more effectively.
NFL HITS HOME RUNS WITH ANALYTICS
Baltimore Ravens, one of the veteran teams of the league, has recently hired two renowned data analysts – Sandy Weil, who studies game trends and helps with scouting decisions; and Eugene Shen, who works with the coaching staff to evaluate player performance. Other teams have followed suit – deploying more and more data analysts to uncover what their players are capable of. Teams in NFL use data analytics in scouting operations for draft and free agency decisions, as well as to improve player health (every team in the league uses an electronic health record that can be accessed by on-field personnel via tablets), a crucial consideration for a sport with a concussion epidemic. Teams with higher aspirations have even advanced to using predictive and prescriptive analytics to enhance their game strategies.
MOTO GP – REVVING THEIR GAME UP
Data analytics has also proved that its usefulness in a game isn’t about physical ability, rather a mechanical genius. A team in MOTO GP named Ducati first leaned on to Machine Learning and Artificial Intelligence to get ahead of the curve. They partnered with Accenture and decided to run prototypes way back in 2012. Despite the constant streams of criticism, the team stuck onto their ideas. The critics raised their voices even higher when trophies were constantly being lifted by Yamahas and Hondas. But persistence eventually led to Ducati’s long-yearned dominance in the game. Data was gathered by the sensors on the bike, which was then thoroughly analyzed. Insights generated from these analyses were used to change the bike configurations considering the necessary variables like track conditions and rubber compounds. Optimized data visualization tools were used to reveal actionable insights for the Ducati engineers; who utilized them to achieve faster lap times for their drivers.
THE EVIDENT CHALLENGES OF USING DATA ANALYTICS IN SPORTS
Needless to say, this entire concept of collecting data and analyzing it in an effort to lift trophies and develop players is not as easy as it seems. Because each and every sport is unique and hence requires different methodologies when it comes to the analyzing aspect of it. The metrics based on which the data shall be collected varies widely as well. Ranging from player profiling to distance management – the key to thriving in sports analytics is to find out the most effective metrics to measure and find out innovative ways to measure them. As the famous saying goes, “The devil is in the details”.
OTHER ASPECTS OF SPORTS ANALYTICS
ASSESSING THE POSSIBILITY OF INJURIES
One of the biggest expenses for any club/team in any sports is the injury of their players. Starting from the treatment of the player to the uncountable match-hours lost, injuries of a few key players can easily make it or break it for a good team any season. In the English Premier League, injuries cost each club an average of $336 million (£250 million) in salary per season and lost them 16 percent more playing days from 2000-15.
Data analytics has proved to be a worthy solution. An analytics company named Kitman Labs have recently worked with the Houston Dynamo of MLS, which led to 76 percent decrease in player unavailability from 476 to 115 days, an 88 percent reduction in strains and sprains, and a 63 percent decrease of in-game injuries, from 11 to four. The Dynamo ended the season in fourth place, after finishing the previous one at the bottom of the league.
Kitman Labs simply analysed data on hamstring injuries to assess the risk factors that the players are being exposed to. The findings revealed that a change in muscle activation patterns resulting from an increased range of motion could cause a higher risk of hamstring injury.
ANALYZING FANS AND MULTIPLE REVENUE STREAMS
Big-name teams have not only restricted data analytics to assess their players’ performances but are now analyzing their ‘consumers’, i.e. their fans/supporters to garner revenue and an increase in profit. Clubs can now use data on their fans to segment them by factors including location, age, and sex. Store sales, hospitality revenue from bars and cafes and season ticket holders can also be monitored, to understand where and when sales are being made in relation to marketing campaigns. Thus, future matches and off-season tours can also be devised accordingly in order to generate more revenue for the club.
The best location for their retail stores can also be set based on the demographics, location, and behaviour of their fans, or boost their ticket sales by analysing past results and balancing the profit margins and purchases through predictive analytics.
Sports has now transformed has a holistic experience. It is not just about which team that you support, it is now about knowing the transfer windows, knowing the possibilities, engaging in social media, taking part in fantasy leagues. The point is – we are not just limited to being ‘viewers’ only. Rather, we have started to become a part of the entire team that we support and a part of the total experience. In such day and age when the consumers of sports have witnessed such paradigm shift in terms of ‘consuming the product’ (i.e. nerve-wracking watching the match), it is needless to say that the ‘product’ requires to experience its fair share of innovation and puts on a greater show for the audience.
By Farhat Chowdhury