[Question] Who is working on structured crowd forecasting?

Platforms like Metaculus aggregate crowd forecasts on unstructured collections of questions. Individual forecasters will often consider structured models relating a number of sub-questions in order to answer a single forecasting question. I’m interested in any work trying to help multiple people jointly produce structured models. I’m interested in cases that could be described as “group collaboration” as well as cases that could be described as “crowd aggregation”. I’m aware that Ought is working on a similar question and I think Guesstimate was motivated by questions along these lines, and I’d like to know if there’s anyone else who is or has been working on something like it.

No comments.