Niklas Wallmeier
All research

Draft2026Expectations and forecasting

Whom to Trust, and When? Aggregating Probability Forecasts in Small Crowds with Short Track Records

Niklas Wallmeier

30 seconds from the problem to the result: why organizations need few people, the simple average and patience with track records.

In short

Should organizations weight forecasters by their track record or take the simple average? A model and 5,898 forecasts by 177 forecasters show that with small crowds and short records, the simple average is hard to beat.

Whom to trust, and when? Try it for your crowd

80%of what averaging can achieve, from this many people
16%of the differences in track records reflect skill rather than luck
19%weight the record deserves; equal weights get the rest

Model of the paper with K0 = 63, estimated from the platform's data: a record of K resolved questions reflects skill to the share K / (K + 63). Crowds with more varied skill learn faster. Unshrunk weights by past accuracy need about twice the critical record length before they pay (Appendix A).

Cite

Niklas Wallmeier (2026). “Whom to Trust, and When? Aggregating Probability Forecasts in Small Crowds with Short Track Records.” Work in progress.

@unpublished{wallmeier2026whom,
  author = {Wallmeier, Niklas},
  title = {{Whom to Trust, and When? Aggregating Probability Forecasts in Small Crowds with Short Track Records}},
  year = {2026},
  note = {Work in progress}
}