PLAYER INJURY FORECASTING AS A METHOD OF SPORTS ANALYTICS
As a result of increased popularity in the use of sports analytics, several methods of sports analytics have been discovered. This is all in an attempt to enhance team’s performance and improve on their chances of winning.
The Sport analytics method we’ll be considering today is Player Injury Forecasting.
WHY PLAYER INJURY FORECASTING?
Injuries suffered by players, either on the field or outside sporting activities has been identified as one of the major reasons for a team poor performance due to an inability of the player to function effectively. It is therefore important that professional teams be able to determine or quantify the likely injury-burden that would be encountered throughout a sporting season.
In an attempt to solve this, a player injury model was invented. This model helps to predict the likelihood that any given player will be injured during an upcoming game.
From a research conducted using SportsVU data model (a tracking technology that can collect positioning data of players during a game) and team information, like player workload and measurements, it was discovered that several factors can greatly increase the risk of player injury, they are:
- The total number of games played;
- The average running speed of a player during games;
- The average distance covered by a player;
- The average number of minutes played; and
- The average number of field goals attempted.
The total number of games played, average number of field attempted and average number of minutes played were identified as workload. Increased workload is naturally connected with greater risk of injury.
Also, the average speed a player ran and average distance covered which is determined by playing style could cause an increased risk of injury.
The player injury model, SportsVU data, can also indicate the probability of a player being injured in upcoming matches. The knowledge of this can help coaches and teams decide when best to schedule their games and when to rest their star players, thus reducing the risk of long-term injuries.
For instance, when the model indicates that a player has a probability of 0.15 or higher percentage of being injured, that player can be advised to rest for the next game.
Analysis has shown that if the top 20% of high risk players were rested for a set time, it could be possible to prevent 60% of all injuries. An alternative approach to this could be to decrease the number of minutes a player plays on the field rather than resting them for an entire game.
In conclusion, team performance would be greatly enhanced if the risks of player injuries are reduced. The use of this method in sports analytics has also been proven to minimize financial costs needed to treat injured players.
In addition to this, a detailed player injury forecasting can help analysts and coaches make the best possible decisions on the field or court.
Apart from improving team sporting performance, player injury forecasting also promotes fan enjoyment and engagement, increase fan loyalty and can increase revenues from ticket pricing
How mature is your team’s analytics program? Take the Sports Analytics Maturity Assessment.
Learn about the Groundbreaking Sports Analytics Model coaches and sports analysts are talking about!
Learn all about Sports Analytics here.