Combining player statistics to predict outcomes of tennis matches

With the growth in sports betting, it is possible to bet, both before and during a match, on a range of outcomes in tennis. This paper shows how the standard statistics published by the ATP can be combined to predict the serving statistics to be obtained when two given players meet. These statistics are then used in a spreadsheet model to predict further match outcomes, such as the length of the match and chance of either player winning. These calculations can be updated as the match progresses. The method is demonstrated by focusing on a very long men's singles match between Roddick and El Aynaoui played at the 2003 Australian Open.