PREDICTIONS

Guide

The predictions table displays a list of upcoming matches. The bars at the centre of the table show the predicted probability of each player winning based on our models.

Above the bars the outright odds from Matchbook are shown where a market is available. We use the Matchbook as they offer the lowest commisions and have a good API which allows for easy automation. Of course if you are using a different bookmaker/exchange please double check the odds on their services.

A simple way to use the table is to multiply the odds by the probability. A number greater than 1 represents "value".

A tennis ball next the player's name is a trade that has been picked based on it having "value" and filtered for certain features such as better recent form.

In the hypothetical example below, its been identifed that there is value in betting on Michael Mmoh. Our model has predicted that their is only a 32% chance of him winning which roughly would equate to odds of 3.13. However on Matchbook they are 3.94 which represents value. Additionally Michael Mmoh has been in better form than his opponent.

Date Player 1 Player 1 Odds Player 2 Odds Player 2
Gilles Muller 1.32 3.94 Michael Mmoh
68%
32%

Below the probablity bars are two sections, Profile and Attributes. These provide some additional comparative statistics which can be used to support your decision process.

Within the Profile section there are a number of subsections which can be opened by clicking on the blue links. These include the last 5 matches and head to head, as well as a chart comparing the players' ranking history.

The Attributes section displays a radar chart with some key comparative features:

  • Win Rate - The player's win rate.
  • Form - The player's recent win rate used as an indicator of form.
  • Surface - The player's win rate on the match surface.
  • Serve - Winning % on serve.
  • Return - Winning % on return.
  • Experience - An indicator for players experience.
  • Reliablity - An indicator for how reliable the outcome for the player is in terms of what has been predicted.
  • Common Op. - Win rate over opponents that are common to both players.
  • Level Win Rate - Win rate over similar ranked opponents.
  • Quality Form - A measure of the quaility of the wins. ie winning against a player ranked 10 in the world counts more than winning against 50 in the rankings.
Mens - Australian Open - Melbourne (Hard)
Date Player 1 Player 1 Odds Player 2 Odds Player 2
In play Filip Krajinovic In play In play Borna Coric
37%
63%
Profile Attributes
In play Alex Bolt In play In play Alexander Zverev
15%
85%
Profile Attributes
19 Jan 2019, 9:30 a.m. Lucas Pouille 1.54 2.83 Alexei Popyrin
58%
42%
Profile Attributes
20 Jan 2019, 2 a.m. Grigor Dimitrov 1.44 3.12 Frances Tiafoe
57%
43%
Profile Attributes
20 Jan 2019, 3:30 a.m. Rafael Nadal 1.18 6.2 Tomas Berdych
84%
16%
Profile Attributes
20 Jan 2019, 6 a.m. Roberto Bautista Agut 2.17 1.83 Marin Cilic
27%
73%
Profile Attributes
20 Jan 2019, 8 a.m. Roger Federer 1.18 6.1 Stefanos Tsitsipas
84%
16%
Profile Attributes
Completed David Goffin 2-6 (3)6-7 3-6 Daniil Medvedev
37%
63%
Profile Attributes
Completed Joao Sousa (6)6-7 1-6 2-6 Kei Nishikori
12%
88%
Profile Attributes
Completed Milos Raonic 6-4 6-4 7-6(6) Pierre-Hugues Herbert
74%
26%
Profile Attributes
Completed Pablo Carreno-Busta 6-2 6-4 2-6 6-4 Fabio Fognini
36%
64%
Profile Attributes
Denis Shapovalov - - Novak Djokovic
8%
92%
Profile Attributes
Mens - Koblenz Challenger (I.hard)
Date Player 1 Player 1 Odds Player 2 Odds Player 2
19 Jan 2019, 2:05 p.m. Gianluca Mager 3.25 1.39 Tallon Griekspoor
48%
52%
Profile Attributes
19 Jan 2019, 3 p.m. Roberto Ortega-Olmedo 1.63 2.36 Pavel Kotov
58%
42%
Profile Attributes
Womens - Australian Open - Melbourne (Hard)
Date Player 1 Player 1 Odds Player 2 Odds Player 2
In play Garbine Muguruza In play In play Timea Bacsinszky
68%
32%
Profile Attributes
In play Venus Williams In play In play Simona Halep
43%
57%
Profile Attributes
19 Jan 2019, 9:30 a.m. Karolina Pliskova 1.61 2.62 Camila Giorgi
76%
24%
Profile Attributes
20 Jan 2019, midnight Amanda Anisimova 2.59 1.61 Petra Kvitova
16%
84%
Profile Attributes
20 Jan 2019, 1:30 a.m. Ashleigh Barty 1.8 2.18 Maria Sharapova
55%
45%
Profile Attributes
20 Jan 2019, 4 a.m. Danielle Rose Collins 6.9 1.15 Angelique Kerber
19%
81%
Profile Attributes
20 Jan 2019, 9:30 a.m. Sloane Stephens 1.65 2.44 Anastasia Pavlyuchenkova
56%
44%
Profile Attributes
Completed Elina Svitolina 4-6 6-4 7-5 Shuai Zhang
69%
31%
Profile Attributes
Completed Madison Keys 6-3 6-2 Elise Mertens
61%
39%
Profile Attributes
Completed Serena Williams 6-2 6-1 Dayana Yastremska
63%
37%
Profile Attributes
Completed Anastasija Sevastova 6-3 6-3 Qiang Wang
63%
37%
Profile Attributes

About us

PROVIDING DATA-LED FORESIGHT ON PROFESSIONAL TENNIS MATCHES

Our purpose is to provide Tennis Brainers the tools and insights to make smarter decisions on their tennis trades. Our models compile data on a huge range of key attributes to unlock hidden advantages and isolate value in the betting markets. From surface, form, age, previous meetings, service speed, to height and weight, we collect and construct hundreds of features that are systematically utilised to build the most accurate predictions on the market. With player level attributes, live pricing and insightful visualisations on meaningful statistics, Tennis Brain adds the power of data and machine learning to tennis trading.

Our algorithms are constantly updated to incorporate new data feeds and trends to consistently achieve returns as the markets and tour evolve. All our predictions are currently free to access, and we are developing to further expand our markets to include set and game scores, providing additional and potentially bigger opportunities within the tennis betting markets. We hope you enjoy the site and make the most of what we believe is an essential tool to successful tennis trading.


Match Predictions

Utilising complex data processing and exhaustive mathematical modelling

Sets & Games Predictions

Currently in development, expanding our service into further markets

Value Identification

Through analysing betting prices across scheduled matches