;)
Thursday, March 15, 2012 at 9:40PM Consider the following scenario. You're offered a bet in which you can choose to predict the final score of the Home or of the Away team and your adversary is then required to predict the final score of the other team.
Sunday, February 19, 2012 at 7:09PM Last season I set Gold Coast's initial MARS Rating to the all-team average of 1,000 and they reeled off 70 point or greater losses in each of their first three outings, making a mockery of that Rating. Keen to avoid repeating the mistake with GWS this year, I've been mulling over my analytic options.
Thursday, February 16, 2012 at 8:58PM In the last blog we looked at Margin Prediction using what I called "bathtub" loss functions. For the current blog I've extended the range of loss functions to include what are called epsilon-insensitive loss functions, which are similar to the "bathtub" loss functions except that they don't treat absolute errors of size greater than M points equally.
Thursday, February 9, 2012 at 8:48PM We know that we can build quite simple, non-linear models to predict the margin of AFL games that will, on average, be within about 30 points of the actual result. So, if you found a bet type for which general margin prediction accuracy was important - where every point of error contributed to your less - then this would be your model. This year we'll be moving into margin betting though, where the goal is to predict within X points of the actual result and being in error by X+1 points is no different from being wrong by X+100 points. In that environment, our all-purpose model might not be the right choice. In this blog I'll be describing a process for creating margin predicting models that specialise in predicting within X points of the final outcome.
Tuesday, January 31, 2012 at 9:24PM It's nice to come up with a new twist on an old idea. This year, in reviewing the relative advantages and disadvantages conferred on each team by the draw, I want to do it a little differently. Specifically, I want to estimate these effects by measuring the proportion of games that I expect each team will win given their actual draw compared to the proportion I'd expect them to win if they played every team twice (yes, that hoary old chestnut in a different guise - that isn't the 'new' bit).
