Foretennis is a system for predicting tennis matches using various methods from the world of machine learning, data mining, predictive analytics, statistics. Foretennis offers unique tennis predictions generated by algorithms, which are working on the tennis big data. At the website you wild find one of a kind tennis predictions and in-depth tennis statistics. Results, fixtures, rankings, tournaments statistics are all available at foretennis. The innovative algorithm uses strict mathematical methods and modern technology to assess many factors and give the best result.
A single foretennis row provides the probabilities for the outcome of the match, prediction for the sets result, odds for the outcome prediction, and result of the match games and sets. The foretennis row looks like this:. Hibino Nao JPN Cibulkova Dominika SVK Pavlyuchenkova Anastasia RUS Sasnovich Aliaksandra BLR Pera Bernarda USA Frech Magdalena POL Lapko Vera BLR King Vania USA Ferro Fiona FRA Wang Xiyu CHN Lisicki Sabine DEU Zvonareva Vera RUS Putintseva Yulia KAZ Cornet Alize FRA Brady Jennifer USA Bogdan Ana ROU Krunic Alexandra SRB Golubic Viktorija CHE Zidansek Tamara SVN Hercog Polona SVN For example, probability to win the title depends on the probability of the player to reach the final as well as probabilities of all players in the other half of the draw to reach the final, multiplied by probabilities for player to win the final match over the each of them.
Sometimes, as initial tournament draws are out, they include unknown qualifiers. Probability for the player to win over the unknown qualifier is determined by variation of the Match Prediction algorithm that includes average Elo Rating and ATP ranking points of the qualifiers as well as winning percentages vs qualifiers, overall and by surface, level, etc Weights of the potential opponents are the probabilities of each opponent to reach the round R.
Match Prediction is based on players' previous results and track records. Match win probabilities given by each of the features neurons are then combined by the neural network using different weights.