Discovering Reliable Causal Rules
This work addresses the challenge of causal inference from observational data for researchers and practitioners in fields like healthcare or policy-making, offering a method to derive actionable rules, though it appears incremental by building on existing causal adjustment techniques.
The authors tackled the problem of inferring reliable causal rules from observational data without controlled experiments, addressing confounding factors and high variance in naive estimations. They proposed a conservative and consistent estimator with an efficient algorithm, showing faster convergence to ground truth on synthetic data and meaningful rule discovery on real-world datasets.
We study the problem of deriving policies, or rules, that when enacted on a complex system, cause a desired outcome. Absent the ability to perform controlled experiments, such rules have to be inferred from past observations of the system's behaviour. This is a challenging problem for two reasons: First, observational effects are often unrepresentative of the underlying causal effect because they are skewed by the presence of confounding factors. Second, naive empirical estimations of a rule's effect have a high variance, and, hence, their maximisation can lead to random results. To address these issues, first we measure the causal effect of a rule from observational data---adjusting for the effect of potential confounders. Importantly, we provide a graphical criteria under which causal rule discovery is possible. Moreover, to discover reliable causal rules from a sample, we propose a conservative and consistent estimator of the causal effect, and derive an efficient and exact algorithm that maximises the estimator. On synthetic data, the proposed estimator converges faster to the ground truth than the naive estimator and recovers relevant causal rules even at small sample sizes. Extensive experiments on a variety of real-world datasets show that the proposed algorithm is efficient and discovers meaningful rules.