Causal inference and policy optimization system based on deep learning models

Abstract

A treatment model that is a first neural network is trained to optimize a treatment loss function based on a treatment variable t using a plurality of observation vectors by regressing t on x,z. The trained treatment model is executed to compute an estimated treatment variable value {circumflex over (t)}for each observation vector. An outcome model that is a second neural network is trained to optimize an outcome loss function by regressing y on xand an estimated treatment variable t. The trained outcome model is executed to compute an estimated first unknown function value {circumflex over (α)}(x) and an estimated second unknown function value {circumflex over (β)}(x) for each observation vector. An influence function value is computed for a parameter of interest using {circumflex over (α)}(x) and {circumflex over (β)}(x). A value is computed for the predefined parameter of interest using the computed influence function value.