Tennis - citations

Tennis (along with football) is one of the most popular sports for in-play trading. There is a wealth of freely available data for which to build trading models.

In-play trading allows the suitably equiped trader to watch and trade the changing fortunes of tennis players whilst matches are in progress.

These academic papers can be found on Google Scholar, JSTOR and in journals stored in university libraries. Some post graduate disertations are listed at the end.

Knottenbelt, William J., Demetris Spanias, and Agnieszka M. Madurska. "A common-opponent stochastic model for predicting the outcome of professional tennis matches." Computers & Mathematics with Applications 64.12 (2012): 3820-3827.

Barnett, T., A. Brown, and S. Clarke. "Developing a Model that Reflects Outcomes of Tennis Matches." Swinburne University (2005).

Barnett, Tristan J., and Stephen R. Clarke. "Using Microsoft Excel to model a tennis match." 6th Conference on Mathematics and Computers in Sport. Queensland, Australia: Bond University, 2002.

Barnett, Tristan J. Mathematical modelling in hierarchical games with specific reference to tennis. Diss. Swinburne University of Technology, 2006.

Barnett, Tristan, and Stephen R. Clarke. "Combining player statistics to predict outcomes of tennis matches." IMA Journal of Management Mathematics 16.2 (2005): 113-120.

Dingle, Nicholas, William Knottenbelt, and Demetris Spanias. "On the (page) ranking of professional tennis players." Computer Performance Engineering. Springer Berlin Heidelberg, 2013. 237-247.

Easton, Stephen, and Katherine Uylangco. "Forecasting outcomes in tennis matches using within-match betting markets." International Journal of Forecasting 26.3 (2010): 564-575.

Newton, Paul K., and Kamran Aslam. "Monte carlo tennis." SIAM review 48.4 (2006): 722-742.

Newton, Paul K., and Joseph B. Keller. "Probability of winning at tennis I. Theory and data." Studies in applied Mathematics 114.3 (2005): 241-269.

Øvregård, Øyvind Norstein. "Trading" in-play" betting Exchange Markets with Artificial Neural Networks." (2008).

del Corral, Julio, and Juan Prieto-Rodriguez. "Are differences in ranks good predictors for Grand Slam tennis matches?." International Journal of Forecasting 26.3 (2010): 551-563.

Also, some post graduate students have produced disertations that are of note.

Aslam, Kamran. A stochastic Markov chain approach for tennis: Monte Carlo simulation and modeling. 2012.

Huang, Xinzhuo, William Knottenbelt, and Jeremy Bradley. "Inferring Tennis Match Progress from In-Play Betting Odds." final year project), Imperial College London, South Kensington Campus, London, SW7 2AZ (2011).



  1. Hi James

    I must not have submitted it properly then. :)

    Let's say that an academic study looked at instances where Event Type X happened in-play during football matches, and found that the market tends to over-estimate the significance of that event.

    Would you agree with me that the study tells us merely about an error that the market made in the past, and the market may self-correct and stop making that error (or even over-compensate and make the opposite error)? If so, how can one profit from academic studies?


    1. A good question. And you are correct in your conclusion.

      There are a variety of reasons why you should read academic papers and why you should take them with a pinch of salt.

      These papers allow you to see the state of the art in the maths and computing used in academia. In that respect they must be read.

      However, what is not always evident is that the paper is often written a year or more before publication. The paper does the rounds until a journal agrees to have it peer reviewed. After review the paper may need revision, which delays further the publication.

      Eventually the paper is published but, by that time, the market inefficiency may already have been discovered by less boastful sports quants.

      The market inefficiency may also not be that profitable anyway so it might not be picked up on by a quant. Often these papers are there to prove a point, which might be more relevant in finance.

      The way to profit from academic papers is to learn the tecniques employed and also to let your mind wander as to alternative uses or alternative angles to attack in the markets.

      I am happy to say that the angles I am working on have not been published and I am in no hurry to publish them either.

  2. Thanks.

    If forecasting models created by mathematicians imply that the odds of an outcome should be x, but the market odds are significantly different, do you assume that the market knows something that isn't accounted for in the models?

    1. Could be either way.

      I would assume the model has been back-tested and shown to be statistically significant. Therefore the model would be more likely to be correct. Alternatively, the model has broken down.

    2. Thanks James.

      By the way, on an unrelated matter, have you ever compared the average trend size of steamers vs drifters in pre-off horse racing markets?

      I sense that drifts are generally stronger, but I've never gathered data to test that hypothesis.

    3. Steamers and drifters are horses that I consider but 'size of' I have never measured and so I don't have the answer you require.

      If you are keen to save time series data from Betfair then take a look at my upcoming article on SmartSigger. You'll be shown how to code a PriceBot (very easily) that will save data for you to test your hypothesis with.

      I recommend SmartSigger. I've met the owner. Nice chap. In it for the love of the sport.

  3. Thanks James

    As regards SmartSigger, I admire people who can make a living from fundamentals, but my personal preference is to simply respond to whatever the market is giving me without taking a view on value. I wish I could make a long-term profit from fundamentals, but I believe that, to make fundamentals pay, you have to be a real expert, as the market price that reflects lots of information and is extremely accurate overall.

    1. I agree with you 100%. That is why I never trade fundamentals and that is probably why I was asked to write articles on bots. The other (technical) side of the trading coin.

      There are other articles in the magazine with plenty of probabalistic and statistical know-how that I find interesting and can be used for technical trading.