Bloomberg has an article today on Elihu Feustel who built a quantitative model to bet on tennis. According to the article, Feustel does not watch a lot of tennis matches but built his model using quantitative inputs to come up with “fair” odds for a match. If his odds are significantly different from what the market is pricing in, he places a bet. I thought there were a few interesting takeaways from his approach.
First, frequently it is possible to build a predictive quantitative model using a few key inputs that does significantly better than the prediction of experts. We have seen this in many different domains. See here for more examples.
Second, before getting carried away and applying this approach into a new domain (investing, for instance), it is important to understand the bounds of this approach. The set of outcomes of a tennis match or a political election is small and bounded. Many investing situations have large possible outcomes. This makes the modeling much more difficult.
Lastly, there may be multiple ways to trade a situation (using options for instance) so the problem is not just one of building a good model but also of figuring out the best trade that maximizes the expected return.
Despite some of the modeling problems, this is an approach worth thinking about more deeply in the context of investing. I have some thoughts on this and I plan to develop this approach in future.
Excerpt from the article:
“Tennis is an “attractive” sport to create an algorithm for because there are only two players in a singles match and statistics are freely available, according to William Knottenbelt, an associate professor of computing at London’s Imperial College. He co-wrote a tennis algorithm that he says would have made a 3.8 percent return on bets on 2,173 ATP matches in 2011.
Feustel, who says he puts in a 60-hour week checking and improving his model, works with a computer programmer and trader. The programmer trawls the Internet for data such as serve speed and break-point conversions. That’s plugged into the model which comes up with “fair” betting prices for scheduled games.
If those odds diverge from market prices, Feustel says, his trader — who lives outside the U.S. — will gamble as much as the market will allow at bookmakers including Pinnacle Sports, based on the Caribbean island of Curacao. That can be about $30,000 on a match result in later tournament rounds.”
Here is a link to the full article.