causal

Simple Averaging of Staked Models Beats Metamodel

Despite building complex machine learning metamodels, Numerai finds that a simple average of staked models is very hard to beat, because staking self-selects the strongest contributors into the ensemble.

causalpending

Speaker

Richard

Evidence Quote

“it's almost like the users are self-selecting by choosing to stake or not”

Source

Crowdsourcing Predictive Algorithms— Invest Like the Best
Created: 11/18/2026, 12:25:04 PM

Your notes

Loading notes...