We’ve had more than a few things to say about the Iowa Electronic Markets over the life of Crooked Timber. In particular, John and myself have defended the view that these markets do not appear to offer marginal information above and beyond published opinion polls.
Some would say that this is fighting talk, and that if we really thought this, we ought to be trying to make some money out of it. So here goes …
Big thanks to Nasi Lemak for sharing a dataset of historical poll data with me. I have used that data to construct and backtest a trading system for the IEM Kerry vote-share contract (KERR) which uses only published poll data and generates favourable backtesting over the last four months. The equity curve for this system so far is below the fold; I plan to use it to trade the IEM vote-share market over the rest of the campaign.
I’m not giving away any details of the system just yet; I’ll reveal them all at the end of the experiment. When the winner-takes-all market is launched, it is quite likely that I will bring another system into play based on trading the WTA contracts as if they were derivatives on the VS market, however that will not affect the current system which is entirely based on publicly available poll data. If I refine the system (currently it only makes use of Bush’s “Approval” ratings, whereas going forward I’d like to drive it off the approval/disapproval spread. I’d also like it to be able to double up and reduce bet size; currently it’s a pretty crude on/off switch), I’ll keep a record of what I did and when. But the proof of the pudding will be in my final P&L; I think that the IEM follows polls rather than leading them, and this is my way of finding out if I’m right. I’ll update as and when the system suggests I trade.
As of today, as the chart above shows, the system is long KERR, which I bought this morning at $0.495. I’ve entered into this trend fairly late, so I’m more or less expecting a few drawdowns early in trading, but if the system works, it ought to be well in profit by November. Wish me luck …
{ 8 comments }
dsquared 05.24.04 at 12:48 pm
NB: I really am setting myself up for a fall on this one, by the way. If you look at the second bar on the chart above, it’s driving nearly half of the entire backtesting performance, and it’s just by pure fluke that the system happened to switch over on the precise peak of one of the bigger volatility spikes during the period in which the KERR contract was settling down post-Iowa. I obviously can’t count on this happening in the future, so I’m just going to hope I can rely on 1) the KERR contract having persistent trends, 2) these trends running roughly in line with the poll data and 3) me being quick enough on the trading button to avoid getting my face ripped off by intraday movements and the bid-ask spread. My guess is that 3) is the biggest risk.
Nasi Lemak 05.24.04 at 3:51 pm
I assumed you wanted the spreadsheet to make some recondite (yet wittily put) point about the fallibility of large populations, not to make your fortune!
dsquared 05.24.04 at 4:07 pm
heh. I’ll cut you in on a share of the profits if there are any … so far there haven’t been any moves at all.
Matthew 05.24.04 at 4:37 pm
Dsquared,
Without giving the details away can you explain what the chart shows? I thought it meant you took positions when the two lines cross, but the most recent one clearly isn’t.
Jason 05.24.04 at 5:28 pm
Kudos to you, win or lose. This is the best way to convince the market-mad people (myself included).
Bill Carone 05.24.04 at 5:49 pm
Dsquared,
Do you have an argument that defeats the people who, disagreeing with the results of your study, simply will say “How unlucky/lucky of Dsquared.”?
For example:
“NB: I really am setting myself up for a fall on this one, by the way.”
So you’ve preemptively explained away any negative result.
Also, I don’t see how this addresses the specific issues with the IEM: small amounts of money bet, relatively large start-up costs for bettors, small number of bettors, etc. So your conclusions may be specific to the IEM as it exists now, and may not help you argue about other markets.
For example, are the following reasonable?
– Small potential profits mean that people will not spend much time and effort making their bets; prices could well be determined by people betting “for fun”.
– This causes the market to be quite slow in incorporating new polling information.
– This allows you to make small amounts of money, not worth your time and effort.
– If just a few other people were doing what you are doing (or even similar things), then you couldn’t make money.
dsquared 05.25.04 at 9:53 pm
Matthew: the positions are shown by the bars; a bar pointing up from the RHS zero axis means that I’m long KERR, a bar pointing down means I’m short.
Bill: well yes, it’s all a bit of fun really. I put the caveats in a comment rather than the main story specifically to avoid making it look like I was trying to excuse failure of the system ahead of time.
All your points are well taken, but I think that any similar market would also have them. Unless we are seriously considering, as a society, diverting material proportions of our savings out of investment in productive assets and into rinkydink “predictive” exercises like this one, this objection is always going to be there.
Kimmitt 05.28.04 at 7:17 am
Isn’t the point of the Iowa markets that they accurately reflect public opinion but far more cheaply?
Comments on this entry are closed.