Li Na defeated Seagate big data analysis with you in-depth analysis

Li Na is a famous world-class tennis player in China, winning a lot of honors for the country and the individual. However, people concerned about the tennis game will not forget that in 2003 that Chinese tennis player Li Na and the United States Serena Williams's US Open tennis women's singles semi-finals. Competition, although Li Na was saved six match points, the final result is still 0-6, 3-6 defeat to Serena Williams, regret to stop the semi-finals. Whether or not fans, we can not help but ask a question: Why did Li lose, is it really trickier, if not, where she lost in the end?

Many people think after the game, Li Na was out because there have been too many mistakes, some people think that Li Na mentality in the game there is a problem ... ... There may be many reasons, but big data analytics tell tennis fans that Li Na did not perform well at this point in the game, and that could be the main reason that led her out.

Li Na why lost to Serena

With each year the United States competition, many tennis fans will visit the official website of the United States directly track the latest progress of the event. The official website of the United States in addition to providing the fastest and the latest event information, but also provides a detailed analysis of each game data.

This data analysis is done with SlamTracker, IBM's intelligent analytics platform. Keys to the match, one of the main features of the SlamTracker platform, is a strategy for winning the ball.

Li Na and Serena Williams in the competition, Li Na party won the key to include three indicators: 1, a hair (first serve) scoring rate of more than 69%; 2,4-9 shoot stalemate in the interest rate to more than 48 %; 3, the service 30-30 or 40-40 scoring rate to more than 67%.

In the actual game, Li Na only completed the second indicator, in contrast, Serena Williams completed two indicators. Therefore, according to this analysis, Li Na out of this mainly with a hair scoring rate is low, the two sides did not get the key points equally divided.

In fact, "Keys to the match" has a different winning strategy for each player, and one of the goals for some players may be that the first-team speed needs to exceed 176 km / h.

In addition, it should be noted that although the SlamTracker set the winning strategy for players, this does not mean that players must complete some or all of the indicators in order to win. In some games, both players may not perform well, failing to meet the SlamTracker set targets.

Big data charm

Normally, "Keys to the match" analyzes each player's historical clash data before the start of each race, and these analyzes give players a key indicator of winning the race. And all of this, all based on big data analysis of all the events of the last 8 years in the US Open.

According to IBM stakeholders, these numbers include nearly 10,000 matches, and for each match, the analyzed data points will be more than 41 million, including scores, rounds, winning points, serve speed, serve success rate, hit the ball Type, hit the number and so on.

Currently, IBM's SlamTracker technology is used in many famous tennis tournaments, and the latest news is that China Tennis Open will also use this technology. For some in the industry, although SlamTracker is not 100% predictive of the outcome of the tennis tournament, the high accuracy has been impressive.

In fact, the charm of big data is not only reflected in the tennis game, there are other cases of sports applications. To prevent injury, the British Leicester Tiger football team used IBM's predictive analytics software.

Through the sensors provided by the players, the team collects and analyzes the data of the 45 players collected to determine which players are more vulnerable and predict the risk of injury to the players and modify the training plan accordingly.

Today, Leicester Tiger football team through predictive analysis to improve the performance of the team with the relevant data such as player physical condition, and each year to enhance the competitiveness of the team.

Data analysis has gone deep into physical activity and is changing the way sports are developed.

As Jeremy Shaw, IBM specializes in business analytics and optimization, points out: "The days of relying solely on talent and intuition are gone."