ATP Ranking Predictions for August 2018

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

Continue reading “ATP Ranking Predictions for August 2018”

Future Insights: Monthly ATP Ranking Forecast

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**):

AppFull

More info below. Continue reading “Future Insights: Monthly ATP Ranking Forecast”

2017 Indian Wells Forecasts

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

Final

Winning Player (rank) Losing Player (rank) W-L %
Roger Federer (10) Stanislas Wawrinka (3) 19-3 72%

Updated 3/18/2017 2 am ET

SF

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%

Continue reading “2017 Indian Wells Forecasts”

2017 Australian Open Predictions

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.

Continue reading “2017 Australian Open Predictions”

Predicting the Winner: 2016 Australian Open

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”

The theory of 1%

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%”

How competitive is men’s tennis?

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

share-of-points-won

We first started at the micro level Continue reading “How competitive is men’s tennis?”

How many points does it take to win?

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?”

Interactive: Tennis Stats, Height, and Age trends on the ATP World Tour

Identifying statistical trends in the men’s tennis game

As part of our data exploration series, we used available datasets, as well as our data to map an increasing trend in height and aces, and a decreasing trend in double faults since 1991.

Story2Pic1

Continue reading “Interactive: Tennis Stats, Height, and Age trends on the ATP World Tour”

Data Exploration: Surface, Serving, and Stature, by the Numbers

We answer how court surface impacts height and serving statistics

Thank you for visiting TenniStats. We are a blog that focuses on the analysis and visualization of tennis data. In this first post, we start by exploring our dataset and sharing some general insights to lay the groundwork for future discussion. Please subscribe to stay up-to-date on our progress!

Picture1 We first examined data for the 2015 season consisting of every men’s singles match played at the ATP 250 level or higher. It contains data points on the tournament, players, and statistics of each match, including points won, aces, and double faults. We examined how court surface impacts these match statistics, as well as how height may give an advantage on different surfaces.

Continue reading “Data Exploration: Surface, Serving, and Stature, by the Numbers”