FLAME: A Fast Large-scale Almost Matching Exactly Approach to Causal Inference

TL;DR

FLAME is a scalable, efficient matching algorithm for high-dimensional categorical data that improves causal inference by providing high-quality matches and estimating treatment effects accurately in large datasets.

Contribution

The paper introduces FLAME, a novel fast matching method that leverages database techniques for scalable, high-quality approximate matching in high-dimensional causal inference.

Findings

FLAME scales to datasets with millions of observations.

FLAME outperforms existing matching methods in accuracy.

FLAME efficiently estimates conditional average treatment effects.

Abstract

A classical problem in causal inference is that of matching, where treatment units need to be matched to control units based on covariate information. In this work, we propose a method that computes high quality almost-exact matches for high-dimensional categorical datasets. This method, called FLAME (Fast Large-scale Almost Matching Exactly), learns a distance metric for matching using a hold-out training data set. In order to perform matching efficiently for large datasets, FLAME leverages techniques that are natural for query processing in the area of database management, and two implementations of FLAME are provided: the first uses SQL queries and the second uses bit-vector techniques. The algorithm starts by constructing matches of the highest quality (exact matches on all covariates), and successively eliminates variables in order to match exactly on as many variables as possible, while still maintaining interpretable high-quality matches and balance between treatment and control groups. We leverage these high quality matches to estimate conditional average treatment effects (CATEs). Our experiments show that FLAME scales to huge datasets with millions of observations where existing state-of-the-art methods fail, and that it achieves significantly better performance than other matching methods.