Chris, in the context of that discussion I meant [*] “prediction market†to also cover the related collective forecasting mechanisms; I wasn’t trying to make a statement on that topic. I have said many times that the main gain is from collecting forecast track records, and that the other differences are less important. Those other differences are not completely unimportant, however.
[*] We need one term for the prediction markets, and another term for the non-trading mechanisms. (“Collective intelligence” is the right tent for both.) Otherwise, it is impossible to discuss. It is a real mess, right now. We are increasing the entropy of the universe. (Same thing with confusing decision markets and decision-aid markets.)
(As for managing track records, it has a cost. The great thing with public real-money prediction markets is that the traders pay for maintaining the exchange.)
NEXT: Predicting = Forecasting –> Collective Forecasting = Collective Intelligence That Predicts
Collective intelligence seems way too broad a term to me – it seems to cover everything from Wikis to Facebook to Blogs.
“collective intelligence that predicts”, something like that…
“predictive collective intelligence”?… 3-word terms don’t succeed, usually…
I the post above that you quoted, I used the term “collective forecasting”; what is wrong with that?
“Forecasting” is sub to “predicting”.
http://en.wikipedia.org/wiki/Forecasting
“Forecasting” is made using a model. Prediction markets and the non-trading collective intelligence mechanisms make use of an information aggregation process —something we billed as completely different.
I bet most people when we tell them the word “forecasting”, they think about “weather forecasting”, i.e., about data and models.
So, I would like to see the result of a poll asking people how they view the term “collective forecasting”. Do they understand that it is an information aggregation mechanism, or do that term “collective forecasting” convey the wrong meaning?
I would abide by the result of that poll.
I fail to see the need for a new term.
Mike,
You are failing to understand the term “forecasting” refers more to model-generated predictions than the other types of predictions.
http://en.wikipedia.org/wiki/Forecasting
QUOTE
Forecasting is the process of estimation in unknown situations. Prediction is a similar, but more general term. Both can refer to estimation of time series, cross-sectional or longitudinal data. Usage can differ between areas of application: for example in hydrology, the terms “forecast” and “forecasting” are sometimes reserved for estimates of values at certain specific future times, while the term “prediction” is used for more general estimates, such as the number of times floods will occur over a long period. Risk and uncertainty are central to forecasting and prediction. Forecasting is used in the practice of Customer Demand Planning in every day business forecasting for manufacturing companies. The discipline of demand planning, also sometimes referred to as supply chain forecasting, embraces both statistical forecasting and a consensus process.
Forecasting is commonly used in discussion of time-series data.
UNQUOTE
“Collective forecasting”
I have asked prof Gelman…
I didn’t make myself clear. I don’t see the need for a term besides PM and CI, that “new” term being forecasting or something else. Though maybe I’m just reacting to the boringness of terminology discussion.
Robin Hanson says that “collective intelligence” does encompass too many things (like wikis and else). So I propose “collective intelligence that predicts”, and we are trying to see whether “collective forecasting” is OK. I don’t think so, because “forecasting” usually relates to predictive modeling, which is very different from our information aggregation mechanisms that gather info from experts and *non-experts* —indeed, a novel thing.
“the boringness of terminology discussion.”
The problem is grave. Robin Hanson is using the term “prediction markets” to describe all the collective intelligence that predicts (including the non-trading mechanisms). That is crazy.
http://www.midasoracle.org/2009/05/22/confusing-prediction-markets-non-trading-collective-intelligence-solutions/
That terminology discussion is necessary.