What Makes a Great Wimbledon Champion

Share this post:

IBM has been supporting Wimbledon’s pursuit of greatness for 27 years. In recent years, much of that contribution has come from the Hursley based Emerging Technology team. This year’s challenge? To find out what makes the greatest Wimbledon champion of all time.

A team of statisticians, tennis analysts, coaches, journalists and developers assembled to start exploring this open ended question. It was clear from the start that each expert had a different point of view about what makes a great Wimbledon champion. And there was a further point of view to consider, that of IBM Watson, a cognitive tool that generates unique insight through its ability to understand natural language and analyse unstructured data.

IBM Watson @ Wimbledon

The Emerging Technology team took the lead on using the cognitive capabilities provided by Watson, like the ability to understand natural language and interpret sentiment, to explore what makes a great Wimbledon champion. We provided Watson with over 25 years of tennis data from articles, blogs and interviews. 350,256 documents in total.

Once the structure of the data was understood, we added the content to the Watson Discovery Service (WDS). With the data stored in WDS, we started to write queries to pinpoint the information we needed. A key benefits to using Watson was how quickly we were set up and extract meaning from the data.  The Watson services lower the barriers to machine learning, allowing developers to solve problems that would previously have required deep AI skills.

To add another dimension to our analysis we explored player personalities using Watson Personality Insights, a service that allows applications to derive insights about personality characteristics. We passed Watson quotes and interview extracts from players. Watson then used linguistic analytics to infer an individuals’ intrinsic personality characteristics, providing us with further insight into what make a great Wimbledon champion.

Watson provides a powerful set of APIs making it possible to run multiple queries with a range of parameters. We found the most efficient way of analysing the 32 players (shortlisted by tennis experts to be the greatest), was to package the API calls into scripts. These scripts would then run the queries, organise the data returned and output the results into spreadsheets. With the query results for each player in this format, we quickly started to identify trends in the data. One great example of this is the data returned from Personality Insights which became instantly digestible the moment it was added to a radar diagram, for instance Andy Murray’s personality profile using the Big Five personality model.


Our analysis gave some fantastic insight into the corpus of unstructured data. In the weeks leading up to Wimbledon, we met with the wider editorial team (statisticians, sports journalists and tennis coaches) to piece together the findings from the different points of view. Sometimes Watson indicated a number of trends that hadn’t yet been seen in the statistics. At other times the statistical data supported the cognitive insights. And on occasions, the cognitive analyses even challenged conventional ideas of greatness.

An example of this was discovering introversion to be a consistent personality trait among the 32 champions. It could easily be perceived that an outgoing, energetic and assertive personality, an extrovert, would help someone progress to the top of a sports career. Watson Personality Insights challenged this stereotype by showing that in fact key characteristics to greatness in tennis are independence, demureness and seriousness.  Introverts make great Wimbledon champions, as described in this article.
One of the biggest challenges was tackling a question where there wasn’t a definitive answer. With Watson, developers are now able to look for answers to subjective questions. Often the questions Watson prompted were as valuable as the insights, leading to an iterative process of discovery.

The Debate Continues #WhatMakesGreat

Although our analysis uncovered some exciting findings, the topic remains up for debate. Each day throughout the tournament The Telegraph will be publishing articles on what makes great. To contribute and add your opinion, get involved in the daily #WhatMakesGreat discussions on Twitter, comment on The Telegraph articles or add your thoughts to Facebook.

Follow @IBM_UK_News and @IBMSports on Twitter for the latest #WhatMakesGreat and IBM@Wimbledon content.

For anyone interested in getting up and running with Watson services, sample code is available showing how to use Watson Discovery Service and Watson Personality Insights. Both services are available to try for free. Discovery Service comes with a data set of news sources that are updated continuously.


More Cognitive stories

IBM Player Spotlight Built with IBM Watson

The Emerging Technology team within IBM Research UK, have been working with FOX Sports to enhance their viewer’s experience of watching ‘The Beautiful Game’. The IBM Player Spotlight Built with IBM Watson is an AI-powered tool built for the FOX Sports’ studio team to access complex statistical analyses using an easy-to-use conversational interface. With the […]

Continue reading

Raise the Game: Cognitive Analysis in Sports

A Clash of Worlds IBM Watson has been used to assist some of the world’s biggest companies and help tackle some of humanities greatest threats. Now, it’s being used to assist Leatherhead Football Club, a team that play in the 7th tier of English Football and are made of up delivery drivers, car salesmen and […]

Continue reading

Cloud Excellence Awards 2017 Winners

The Cloud Excellence Awards for 2017 were held on 20th September with a winning place given to one of the project ETS have been working on.  The evening event was held at a hotel in London and was well attended by many of the candidates.  There were a wide variety of submissions in the various categories […]

Continue reading