They do slightly worse than simply averaging a bunch of estimates, and would be blown out of the water by even a naive histocratic algorithm (weighted average based on past predictor performance using Bayes)
Fantastic. Please tell me which markets this applies to and link to the source of the algorithm that gives me all the free money.
Unfortunately you need access to a comparably-sized bunch of estimates in order to beat the market. You can’t quite back it out of a prediction market’s transaction history. And the amount of money to be made is small in any event because there’s just not enough participation in the markets.
And the amount of money to be made is small in any event because there’s just not enough participation in the markets.
Aren’t prediction markets just a special case of financial markets? (Or vice versa.) Then if your algorithm could outperform prediction markets, it could also outperform the financial ones, where there is lots of money to be made.
In prediction markets, you are betting money on your probability estimates of various things X happening. On financial markets, you are betting money on your probability estimates of the same things X, plus your estimate of the effect of X on the prices of various stocks or commodities.
The IARPA expert aggregation exercises look plausible, and have supposedly done all right predicting geopolitical events. I would not be shocked if the first to use those methods on financial markets got a bit of alpha.
Fantastic. Please tell me which markets this applies to and link to the source of the algorithm that gives me all the free money.
Unfortunately you need access to a comparably-sized bunch of estimates in order to beat the market. You can’t quite back it out of a prediction market’s transaction history. And the amount of money to be made is small in any event because there’s just not enough participation in the markets.
Aren’t prediction markets just a special case of financial markets? (Or vice versa.) Then if your algorithm could outperform prediction markets, it could also outperform the financial ones, where there is lots of money to be made.
In prediction markets, you are betting money on your probability estimates of various things X happening. On financial markets, you are betting money on your probability estimates of the same things X, plus your estimate of the effect of X on the prices of various stocks or commodities.
The IARPA expert aggregation exercises look plausible, and have supposedly done all right predicting geopolitical events. I would not be shocked if the first to use those methods on financial markets got a bit of alpha.