Use of Data Analytics in Sports
-By Naman Jain
For Hollywood aficionados, the 2011 film Moneyball was a sneak peek into an up-and-coming profession where both the sports enthusiast and a data-cruncher resided in the same person. In the movie, the duo of Billy Beane and Peter Brand revolutionised the world of sports with the implementation of data-driven decisions.
The use of decisions backed by data can also be observed in the case of the British Cycling Team, which, under Dave Brailsford, the performance director, made several seemingly insignificant changes to the everyday routine (from the pillow they sleep on, to the way they wash their hands) of each cyclist, ultimately propelling them to dominate the 2008 Beijing Olympics.
This tryst of data with the world of sports has a multitude of examples as its testimony and is an exciting area that Generation Z is excited to dabble into.
Want to know when a bowler bowls their best? Use data. Want to know which player is underperforming on the football field? Use data. From an attitude characterised by disdain, today sports teams and boards are increasingly hiring people proficient in working with huge chunks of data to maximise their team’s performance. Let’s look at some of the data’s applications on the field.
- Ball Tracking: With the development of the Hawk-Eye System and the triangulation of the video feeds of several cameras, the path travelled by a ball can be judged with a high degree of accuracy. Although not infallible, the Hawk-Eye System is often considered an impartial second opinion, and its decision is respected in situations of dispute.
- Telemetry: During F1 races, the race cars have to make pit stops wherein the team makes certain adjustments and changes to the car so as to optimise performance. These decisions are taken on the basis of real-time data obtained by sensors integrated in the car that transmit the condition of the car every passing second.
- Tracking Player Health and Nutrition: Of course, the brand value of a sports team depends on the key players being present on the field. Teams do not shell out a large sum of money for a rising player only to not see them in the season owing to injury. Hence, investing in the health and fitness of a player becomes crucial. With the emergence of an intensively competitive market for smart wearables, players and teams now have the technology to measure the oxygen and glucose levels of a player and even their sleep cycles. Ensuring an optimum level of such factors will significantly decrease the chance of an injury.
- Player Performance and Team Strategy: The proper analysis of the on-field performances of players allows the team management to decide which players play the best at which positions, which team combination generates the most synergies, and from where the best shots are taken. Teams can use this data to try out new playing line-ups and accordingly decide on a playing style most suited to the players on their roster.
Some of the applications of data analytics off-the-field are:
- Sports Gambling: The cradle of the analytics-based sports gambling industry lies in the founding of Sportradar by Dr. David Schwartz in 1997. By accumulating data from a variety of sources on various parameters such as player’s performance, the team’s overall performance, and other key metrics, coupled with technologies like Big Data, which can calculate the odds of a particular event, a professional gambler can take calculated risks to earn returns.
- Player Valuations: Often when we see player auctions for big sporting leagues, we are left to wonder: who determines the price that a team is paying for the player? This price is determined by a number of factors, like consistency, overall performance, and performance at diverse locations and in diverse conditions. The teams organise play-by-play data and, using machine learning algorithms, find data for the above parameters. Through the analysis of this data, the teams are able to figure out how well a player would fit into the existing team.
- Pricing Strategy: Most teams benefit when their team is playing at their home grounds, as they earn from the sale of tickets for the game. This forms a significant part of their total revenue. By analysing historical data and the impact of new developments like the signing of a popular player, the competing team, and the current performance of the home team, the teams can estimate what the turnover and footfall would be. Ultimately, this would allow them to price the tickets for the game appropriately and maximise their revenue.
The sports analytics industry is a fast-growing one and is currently valued at US$2.22 billion. It is projected to reach US$12.6 billion by 2029 at a CAGR of 28.1%. Companies like Sportradar, Whup, Kitman Labs, and Hudl are the pioneers in this industry. It can be argued that such firms are differentiating themselves from run-of-the-mill data analytics firms and venturing into a new and booming area, thereby employing the blue ocean strategy.
Ever since the development of technologies like Machine Learning, Artificial Intelligence, and Natural Language Processing, this industry has expanded and taken in a wide variety of applications. The users of this industry include both professional gamblers looking to turn a profit from the performance of their favourite player and team management, who want to lift the trophy while also ensuring that their players are injury-free.
The future of the industry indeed looks bright. With the introduction of various short-form leagues around the world, like the IPL in India, which puts spectator experience at the forefront, teams will have to rely more and more on sports analytics. Firms may also look to improve the experience the spectators have at the stadiums and arenas, not just that of watching their teams play. This might include using analytics to find out if providing more services at the stadium (for instance, the opening of quick-service restaurants) might give them increasing returns.
In a nutshell, it is an exciting time for the sports analytics industry, and there are various interesting developments that one should look out for in the future.
- Clear, J. (2020, February 4). Marginal Gains: This Coach Improved Every Tiny Thing by 1 Percent. James Clear. https://jamesclear.com/marginal-gains
- Schroer, A. (2022, January 12). How Sports Analytics Are Used Today, by Teams and Fans. Built In. https://builtin.com/big-data/big-data-companies-sports
- Wikipedia contributors. (2022, December 18). Hawk-Eye. Wikipedia. https://en.wikipedia.org/wiki/Hawk-Eye
- Woodie, A. (2021, March 18). Five Real-World Applications for Sports Analytics. Datanami. https://www.datanami.com/2021/03/18/five-real-world-applications-for-sports-analytics/
- Ahmed, N. (2022, December 29). Understanding Sports Data Analytics Simplified. Learn | Hevo. https://hevodata.com/learn/sports-data-analytics/
- Ghosh, A. (2022, June 5). How Sports Analytics is Changing the World of Gambling. The Customize Windows. https://thecustomizewindows.com/2022/06/how-sports-analytics-is-changing-the-world-of-gambling/
- Sports Analytics Market Size, Share & COVID-19 Impact Analysis, By Deployment (Cloud and On-premises), By Type (On Field and Off Field), By Solution (Video Analytics, Bio Analytics, Smart Wearable Technology, and Others), By Technology (AI, Big Data, and Others), By End-user (Individual and Teams), and Regional Forecast, 2022-2029. (n.d.). https://www.fortunebusinessinsights.com/sports-analytics-market-102217