Skip to content

Monitoring ML-based risk prediction algorithms in the presence of confounding medical interventions

Notifications You must be signed in to change notification settings

jjfeng/monitoring_ML_performativity

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 

Repository files navigation

Companion code for the manuscript "Monitoring machine learning (ML)-based risk prediction algorithms in the presence of performativity"

To appear in AISTATS 2024

Installation instructions

  • This code is designed for running with pip. Packages are listed in requirements.txt.
  • To run the Bayesian changepoint monitoring procedure, install cmdstanpy and stan.

Reproducing simulations

Code for each simulation is organized in a folder with the prefix simulation_. Use scons to run these simulations, e.g. scons simulation_null_naive.

About

Monitoring ML-based risk prediction algorithms in the presence of confounding medical interventions

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published