Analytics Helps to Reduce Injuries to Rugby Players

Professional sports are much more than just a game. Instead, they are increasingly becoming a scientific undertaking that is driven by data and numbers. Gone are the days of relying on raw talent and gut instinct to succeed. Although sports organizations have used analytics for years-the book and fi lm Moneyball highlights the use of analytics to make player decisions in major league baseball in the 1990s-analytics software is becoming ever-more sophisticated. The use of analytics is now spreading to professional rugby, a popular sport in Great Britain that bears some resemblance to U.S. football. Rugby historically has been a brutal contact sport in which players use minimal protective equipment.

In fact, about 25 percent of all players are injured during a typical season, and some suffer season-ending injuries. For the players, the injuries are frustrating and can cause them to sit out games, sometimes even an entire season. For the teams, the absence of key players on the fi eld frequently results in lost games, as well as diminished ticket sales and attendance. Teams such as the Leicester Tigers in the United Kingdom are now embracing analytics to conduct deep analyses of raw injury data. The Tigers worked with IBM to develop more effi cient methods to understand why injuries occur and how the organization can reduce their frequency. Analysts studied a variety of factors, including fatigue and game intensity levels, to detect hidden patterns and anomalies that provide insights into which players were likely to get injured and what types of injuries they would suffer.

For example, if a player displays a statistically signifi cant change in one or more of his fatigue parameters (e.g., the level of lactic acid in his blood is statistically too high) and the current intensity level of training is high, these data might indicate that his chances of being injured are 80 percent greater than normal. One of his teammates might register a 60 percent greater risk. This level of real-time information makes it possible for the team to adjust each player's training regimen as well as the team's substitution patterns in games to reduce the risk of injury. Going further, analytics allows the Tigers to analyze psychological data to reveal other key factors that could affect their players' performance. These factors include the additional stress of playing on the road, as well as social or environmental elements (e.g., family problems) that could impact the way players perform during a match. The goal is to tailor the team's training programs to each player's physical and psychological state. Sources: Compiled from A. Smith, "Sports Analytics: How ‘Moneyball' Meets Big Data," ZDNet, March 14, 2013; R. Bluey, "From ‘Moneyball' to Money Bombs: What Sports Analytics Can Teach Political Nerds," The Atlantic, March 8, 2013; P. Dizikes, "Sports Analytics: A Real GameChanger," MIT News, March 4, 2013; S. Greengard, "Putting Predictive Analytics Into Play," Baseline Magazine, May 2, 2012; B. Alamar and V. Mehrotra, "Beyond Moneyball: The Future of Sports Analytics," Analytics Magazine, February 24, 2012; www.leicestertigers.com, accessed April 3, 2013.

Questions

1. If you were a player for the Leicester Tigers, would you want to have that much personal data analyzed? Is there a "creepiness" factor here? Support your answer.

2. What are some potential disadvantages of Leicester's analytics system? Provide specific examples.

3. Would you encourage your favorite U.S. sports teams to adopt a similar analytics system? Why or why not?