I grew up playing tennis on the red clay courts of the Czech Republic in the early 1990’s. I received my first tennis racket from Martina Navratilova at the same tennis club where she grew up. Almost 25 years later, I met her at the Czech Embassy in Washington, DC and she signed it for me, saying, “I hope it treated you well through the years.”
Continue reading “My Story Growing Up Playing Tennis in the Czech Republic”
We use our machine learning model to predict ATP rankings
In our last blog post, we detailed our new machine learning forecasting app that predicts future rankings. The app updates automatically on a weekly cadence and we’ve pulled the most recent results into 2 tables below.
The current top 10 ATP players are forecasted to remain stagnant into August. This is after Zverev defended his title at the Citi Open and last week’s tournaments have been accounted for.
| Name | July Rank | Aug. Rank Pred. | July Pts. | Aug. Pt. Pred. | Rank Diff. |
| Rafael Nadal | 1 | 1 | 9175 | 9248 | 0 |
| Roger Federer | 2 | 2 | 7490 | 7167 | 0 |
| Alexander Zverev | 3 | 3 | 5688 | 5785 | 0 |
| Juan Martin del Potro | 4 | 4 | 5316 | 5457 | 0 |
| Kevin Anderson | 5.8 | 5 | 4400 | 4650 | -0.8 |
| Grigor Dimitrov | 6 | 6 | 4652 | 4462 | 0 |
| Marin Cilic | 6.5 | 7 | 4194 | 4000 | 0.5 |
| Dominic Thiem | 8 | 8 | 3708 | 3899 | 0 |
| John Isner | 9 | 9 | 3436 | 3561 | 0 |
| David Goffin | 10.5 | 11 | 3118 | 3074 | 0.5 |
How recent ATP player trends impact future rankings before they happen, updated live
Welcome back tennis fans… and no, we didn’t forget about your thirst for tennis and data analytics! Our new web app allows you to easily see a player’s ranking history, similar to the ATP site, but with an added ranking forecast, packaged as an interactive visualization not available anywhere else!*
Check out the app here (15 second load time**):
More info below. Continue reading “Future Insights: Monthly ATP Ranking Forecast”
New match database that contains top players such as Phil Dalhausser, Nick Lucena, Kerri Walsh, and April Ross
Welcome to BigTimeStats, the TenniStats rebrand, now with beach volleyball match data. Drawing inspiration from Jeff Sackmann’s tennis match database, I’ve compiled all AVP and FIVB matches going back to year 2000, available as open source csv/excel files on Github. Continue reading “AVP & FIVB Beach Volleyball Match Database”
Blogging from the bush, we’re bringing you our latest forecasts
We are on site in the California desert, bringing you our predictions for the 2017 Indian Wells BNP Paribas Open.
Updated 3/19/2017 1:45 pm ET
| Winning Player (rank) | Losing Player (rank) | W-L | % |
| Roger Federer (10) | Stanislas Wawrinka (3) | 19-3 | 72% |
Updated 3/18/2017 2 am ET
| Winning Player (rank) | Losing Player (rank) | W-L | % |
| Stanislas Wawrinka (3) | Pablo Carreno Busta (23) | 2-0 | 76% |
| Roger Federer (10) | Jack Sock (18) | 2-0 | 83% |
We use our predictive model to forecast unplayed tennis matches
Update 1/27/2017 6:05 pm
Final Predictions
| Winning Player | Losing Player | W-L | % |
| Roger Federer (17) | Rafael Nadal (9) | 11-23 | 73% |
SF Results
2/2 matches correct
Update 1/25/17 6:45 pm
SF Predictions
| Winning Player (rank) | Lossing Player (rank) | W-L | % |
| Roger Federer (17) | Stanislas Wawrinka (4) | 18-3 | 83% |
| Rafael Nadal (9) | Grigor Dimitrov (15) | 7-1 | 62% |
QF Results
2/4 matches correct.
Creating an algorithm for tennis match forecasting
So far, we’ve covered general descriptive statistics, such as yearly attribute trends, points won distributions, and competitiveness on our blog. We build on those findings by creating a model capable of predicting ATP tennis match winners. Using historical data points, we achieve 81% accuracy in predicting match winners for the 2016 Australian Open. We delve into the development process and share our predictions below.
Continue reading “Predicting the Winner: 2016 Australian Open”
For several top players, a 1% increase in points won means cutting their ranking by half.
I recently came across an article by Craig O’Shannessey on atpworldtour.com which talked about the huge difference a 1% increase in points won can have on a players ranking. The article quotes stats from Dominic Thiem’s 2014 and 2015 seasons, in which he jumped from number 40 to number Continue reading “The theory of 1%”
We compare points, games, sets and other statistics from 1968 to today in order to answer how tennis has evolved.
One of the first things to consider when assessing the competitiveness of any sport is how many points are scored by opposing players and teams. In basketball, for example, a score line of 101-99 is way more competitive than 130-70, even though the total points scored is the same. In tennis, results are dictated by a scoring hierarchy (point-game-set-match), therefore, there are many ways to judge the competiveness of a match. Tracking each of these scoring numbers over the years reveals just how much the competition has evolved – or stayed the same…
By Points
We first started at the micro level Continue reading “How competitive is men’s tennis?”
We broke down points won and lost per match from 2005 to 2015 and found some basic winning odds. Turns out, slight advantages in points won can tip the scales significantly.
Points are the most basic scoring unit in tennis, but they do not directly determine the outcome of a match. To win a match, you must string together combinations of points into games and games into sets, etc. Certain points can be “thrown away” while others can single-handedly determine the outcome of the match. Continue reading “How many points does it take to win?”
BigTime Stats 