Thank you for including Replication Markets! A couple of notes:
Yes, the survey round is potentially a Keynesian beauty contest, though it takes some doing. You’re not forecasting the market round. You’re forecasting the best estimate we can make using peer prediction on the independent surveys. Harvard’s peer prediction algorithm has done well in previous tests, and in theory takes a lot of coordination to defeat.* The truth is probably a good bet. We’ll know more in December.
We had originally planned to use the output of surveys to set the market starting prices—but it made for a very messy experimental design. So we used a 70% accurate decision tree. It wasn’t intended to be secret—I thought we had stated it fully but searching the site I find only oblique references.
*We got to test that a bit in Round 8 when we discovered a coordinated “attack” that accounted for ~1/3 of our surveys. Some forecasts would have changed, prizes would have been won, but neither so much as we feared.
Thank you for including Replication Markets! A couple of notes:
Yes, the survey round is potentially a Keynesian beauty contest, though it takes some doing. You’re not forecasting the market round. You’re forecasting the best estimate we can make using peer prediction on the independent surveys. Harvard’s peer prediction algorithm has done well in previous tests, and in theory takes a lot of coordination to defeat.* The truth is probably a good bet. We’ll know more in December.
We had originally planned to use the output of surveys to set the market starting prices—but it made for a very messy experimental design. So we used a 70% accurate decision tree. It wasn’t intended to be secret—I thought we had stated it fully but searching the site I find only oblique references.
*We got to test that a bit in Round 8 when we discovered a coordinated “attack” that accounted for ~1/3 of our surveys. Some forecasts would have changed, prizes would have been won, but neither so much as we feared.