FIFA 2010 coming up.. should we update the World Cup Predictor?

[mouser]

It's hard to believe it's been almost 4 years since the online FIFA World Cup 2006 Predictor went live.. it didn't seem to get much attention or use.

https://www.donation...dex.php?topic=3872.0

I'm wondering if it's worth the trouble to update it for 2010.. Thoughts?

[rgdot]

As a big soccer (football) supporter and follower I would be interested

[TucknDar]

Me too!! I was too new to DC back then to use it, but I'd do it now

[anodyne]

I'd like to see it updated too.  I'm not an expert, but I'd be happy to try to dig up some representative scores between teams (seems like that's what you needed last time).  One issue: teams from different conferences (e.g. Brazil & Germany) don't play each other competitively very often (pretty much only in the finals of the World Cup).  So getting rankings across conferences could be tricky.

[bgd77]

I would like to see it too. And, if necessary, I'll try to help you with data or whatever it is required.

[mouser]

After spending the last few weeks doing heavy duty javascript for my new http://www.tfdocs.com site, and having an absolute ball, i think i can pretty much guarantee that i will update the world cup predictor for 2010.

[rgdot]

Looking forward to it and ready to help if needed as well

[bgd77]

After spending the last few weeks doing heavy duty javascript for my new http://www.tfdocs.com site, and having an absolute ball, i think i can pretty much guarantee that i will update the world cup predictor for 2010.

-mouser (November 14, 2009, 09:21 PM)

Hurray!!! 

Lookoing forward to it. 

[mouser]

now who's going to put some money down based on WCP preductions?

here's the post i made about the 2006 WCP results:
https://www.donation...dex.php?topic=4296.0

remember that the program is not designed to predict who will win per se, that is exceedingly easy.  it's designed to tell you who has the best odds to bet on!

[bgd77]

Me. Although I do generally do not gamble, in the interest of testing the program I will put my money in it. 

[TucknDar]

Considering I'm finally done with my education in time for the WC, I guess I can celebrate by putting in some cash

[kakarukeys]

I will be interested in any rule-based system that could predict match result. Probability theory is good but the bookmakers use it to set the odds too, you can beat them with what they already know.

[kakarukeys]

I mean you can't 

[mouser]

actually people can and do make a living betting on such public things -- betting on the horses is a good example.

the key is that you don't have to beat the house/bookmaker, the way you do when playing roulette in a casino -- you only have to be better than the other bettors.

[mouser]

Pretty much done updating it for 2010.
Odds aren't correct because I haven't written scraping code yet.
And the there are no good expert ratings yet (please add some!).

Should be ready by Jan 1, 2010.

Now the trick is going to be finding some people to put in some good pairwise score estimates (see here for more info).

[mouser]

Update:
I've loaded it up with some current betting odds found on the web.

So it's ready to roll.. Though it's missing any expert ratings so it's not going to be of much use until then.


However, if you want to get a feel for how this tool for calculating betting advice differs from a tool to predict the winner -- select the "Uniform Ratings" from expert ratings list, click Load, then Start the simulation.

What you should see over time is now every team equally likely to win the tournament.  Now look at the Expected Profit columns.  Red entries are expected profitable bets, the higher the better.  Note that Honduras is the highest expected payoff -- which makes sense since it's the team that has the highest payoff odds and we are assuming for this experiment that all teams are equally likely to win.

[LOCKING TOPIC -- PLEASE REPLY ON ONE OF THE ACTIVE WCP 2010 THREADS]