Performance to Date

You might imagine that the model could be pitted against the bookmaker odds. And you are correct! In fact, if you were to do this since the start of 2005 to the current round your bank would look something like this:


That is to say, if you had $1 at the start, and bet on every game the model suggests, you would have over $17 now. The model suggests not only which teams to bet on, but also how much to bet on them. This point is crucial to long-term growth. Betting equal amounts on every game is a path to financial ruin.

An interesting feature of the graph is that almost all of the winners it picks are home teams. Fascinating.

Note that I have only been generating probabilities since the start of the 2012 season, and only publishing them on this website since June of 2013.



      1. Thanks. It looks like returns have been more or less flat since the 1000 game mark. Any idea why that is? Could mean the system is not profitable now, maybe to do with changes by bookies (odds) if any? Or is it just best now to bet from the troughs in that range?

      2. It is an interesting observation, and one I have given some thought to. It could be that the bookies have improved in the last few years. This year, particularly, however, the favourites have been winning even more often than they should, which has hurt returns. Yet we’ve still turned a profit this year. Another possibility is that GWS and Gold Coast have played in a lot of blow outs, which could skew the ratings. I’m going to wait until the end of this season to reassess how the model is performing.

  1. I obviously have no idea how the predictions are generated, but the sideways range does seem to start when Gold Coast entered. Melbourne has been just as poor the last 2-3 seasons. Interested to know if that is the reason. Hopefully things are on the up now, at least for Gold Coast and Melbourne. GWS are still struggling.

    1. It seems to be that the last few years, underdogs haven’t quite been able to get over the line and win as many games as in the past. Perhaps this has something to do with the gap between the best and the worst in the competition being larger. I would be interested to see how line betting has performed in the same period – hopefully I’ll have some of this data by the end of the season.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s