Improving Causal Effect Estimation of Weighted RegressionBased Estimator using Neural Networks

TL;DR

This paper introduces a neural network-based estimator to improve causal effect estimation from observational data, especially in high-dimensional and limited-sample scenarios, outperforming existing methods by up to 55%.

Contribution

The paper proposes a novel neural network approach that enhances the accuracy of causal effect estimation in complex, high-dimensional, and finite-sample settings.

Findings

Neural network estimator significantly outperforms state-of-the-art methods.

Solution quality improves by up to 55% with the proposed method.

Effective in non-linear, high-dimensional, and limited data scenarios.

Abstract

Estimating causal effects from observational data informs us about which factors are important in an autonomous system, and enables us to take better decisions. This is important because it has applications in selecting a treatment in medical systems or making better strategies in industries or making better policies for our government or even the society. Unavailability of complete data, coupled with high cardinality of data, makes this estimation task computationally intractable. Recently, a regression-based weighted estimator has been introduced that is capable of producing solution using bounded samples of a given problem. However, as the data dimension increases, the solution produced by the regression-based method degrades. Against this background, we introduce a neural network based estimator that improves the solution quality in case of non-linear and finitude of samples. Finally, our empirical evaluation illustrates a significant improvement of solution quality, up to around $55\%$, compared to the state-of-the-art estimators.