no code implementations • 14 Sep 2023 • Nilesh Tripuraneni, Lee Richardson, Alexander D'Amour, Jacopo Soriano, Steve Yadlowsky
We introduce a new statistical framework to both define and construct an optimal proxy metric for use in a homogeneous population of randomized experiments.
no code implementations • 3 Jul 2023 • Lee Richardson, Alessandro Zito, Dylan Greaves, Jacopo Soriano
The two most significant issues are 1) low sensitivity of the north star metric and 2) differences between the short-term and long-term impact on the north star metric.