Big data in sports
Big data refers to a large, variable and diverse dataset in which analysis is problematic but also can be worthwhile for leading to an acquisition of knowledge. Big data is generally characterized by the 3Vs(volume, variety and velocity).
- volume - the quantity of data
- variety - the data transfer rate
- velocity - diversity of the dataset
Early history of sports analysis
Already in 1858, Henry Chadwick invented the box score-a summary of the results from a sport competition. That invention is said to be the first instrument that helped statisticians describe diversified aspects of the game in baseball by numbers. He is also credited for developing statistics such as batting average and earned run average. Likewise, the value over replacement player (or VORP) was instrumental in sports analysis. These statistics feature on the impact a hitter or pitcher on the team progress in comparison to a bench warmer who is an average fielder at that position[1]. Sports analysis becomes part and parcel of this area, collecting, and scrutiny that figures helps coaches, players and other staff in decision-making relating to sports events. The following categories are distinguished in particular: on-field and off-field analytics. The first one inquires in aspects like player fitness and game tactics, it pertains to improving the capability of players and groups on the pitch. Off-field analytics handle with the business sector of sports.
Using big data in sports
Breakthrough was using Big data in sports. As the first implemented it the baseball club Oakland Athletics in 2002 when right before the season was beginning the team lost three players. That's when their manager Billy Beane and his assistant Paul DePodesta were looking for their successors on the grounds of computers analysis. They were supporters of the sabermetrics - analysis of baseball, particularly baseball statistics that mete action in a match[2]. Beane and DePodesta checked for big data to see what is the impact on winning the baseball game. After resolving accrued information they concluded that widely rated metrics didn't have such a big impact on the result of the match.They found out other overlooked metrics had the most powerful interdependence with winning. Beane and DePodesta finally found the combination of players they want to take on to the team[3]. Not everyone was for that squad but the manager faced the criticism. Owing to that fact the Oakland Athletics won the next 20 matches and beat the Premier League record[4]. The aforementioned occurrence was published year after by Michael Lewis in the book "Moneyball: The Art of Winning an Unfair Game". The film based on that book was released in 2011, starring Brad Pitt and Jonah Hill. Nowadays abused big data is widespread almost in every sports category.
Footnotes
| Big data in sports — recommended articles |
| Measurement of innovation — Alfred Sloan — Strategic planning tools — Geodemographic segmentation — Descriptive statistics — Behavioral data — Analytical sheet — Pareto chart — Black box model |
References
- Fried G., Mamcu C. (2017), Sport Analytics: A data-driven approach to sport business and management.
- Galbraith J.R. (2014), Organization Design Challenges Resulting From Big Data.
- Goldsberry K., Ph.D. (2012), CourtVision: New Visual and Spatial Analytics for the NBA.
- Lewis M. (2002), Moneyball-The Art of Winning an Unfair Game, 5-20.
- Wang L., Shao J., Cao R. (2016), A Novel Modified Simulated Annealing Algorithm and Big Data Sampling Analysis based Sports Effect Evaluation Model.
Author: Adrianna Lisak
