How Infosys Information Platform Helped Tennis Fans See More
ATP Tour, Inc. (ATP) is the governing body of men’s professional tennis circuits – the ATP World Tour. With 62 tournaments in 31 countries, the ATP World Tour showcases the best of tennis in the world’s most exciting venues. Seeking to enhance the tennis experience for its fans and players, ATP partnered with Infosys, to explore the possibility of creating a new analytical series that dwells deeper into what statistics can reveal about player performance. Further it plans to showcase how historical data around player performance, their strengths and weaknesses can be used to predict player behaviour, their shot selection and finally the outcome of the match itself.
To develop, test and arrive at the optimal probability analytics approach, Infosys focused its knowledge curation efforts on umpire data captured by ATP across all tournaments over the last 12 months and 5 years of the Hawkeye data from the Barclays ATP World Tour Finals.
The team then sought to select the right open source analytics platform (as against traditional BI tools) to provide timely insights. Open source technologies can perform complex analytics on massive quantities of structured and unstructured information using commodity hardware at a fraction of the cost. Traditional BI tools are able to process only a fractional amount of data in a limited number of formats using a laborious ETL (Extract Transform Load) methodology to its data warehouse to deliver a report, which can sometimes take hours or even days. Infosys Information Platform (IIP), our open source data analytics platform proved to be an ideal choice as it could extract (voluminous and variegated) data very quickly from a vast data lake to transform it on the fly and provide insights almost instantaneously through unbroken seamless interaction. Leveraging just 2 nodes of 8 Core CPU and 16GB RAM for hardware, IIP was fully equipped to process data volumes of over 240,000 records (12 million data points) in near real-time! Providing, a repertoire of in-depth player performance probability-led foresight to media and game commentators, while also publishing live on
ATPWorldTour.com select insights about match outcome probabilities.
Probability was established and published for the following:
- Speed of shots of each player, also against each other for both forehand and backhand
- Speed of first serve, second serve, aces of each player, also against each other
- Speed of serve across a match at different time slices
- Point winning shots by backhand and forehand for each player, also against each other
- Winning statistics of each player against each other at different surface types
- Holding statistics of each player at different game scores; breaking statistics of each player at different game scores
- Double fault, match winning streaks, first serve return, , match points saved for each player
- Fatigue indexes- based on court-time spent on court this year, average time to play sets, average time to win a set
- Serve Analysis- Based on hawk eye data for direction/placement of serve (out wide v/s mid-way into body or down the T)
- Based on point of match where is the serve placed from deuce/ad court, ace count analysis on different points of a match
Based on the analysis, high probability factors influencing match outcomes were published as insights, in real time, on
ATPWorldTour.com for tennis fans.