Causal Mechanism-based Model Construction

TL;DR

This paper introduces a framework for constructing graphical causal models based on causal mechanisms, enhancing interpretability and manipulation prediction, implemented as an interactive module in existing modeling tools.

Contribution

It presents a novel causal mechanism-based framework for graphical model construction, integrated into widely used modeling software for practical usability.

Findings

Supports intuitive understanding of causal relationships

Enables prediction of effects of interventions

Implemented as an interactive module in SMILE and GeNIe

Abstract

We propose a framework for building graphical causal model that is based on the concept of causal mechanisms. Causal models are intuitive for human users and, more importantly, support the prediction of the effect of manipulation. We describe an implementation of the proposed framework as an interactive model construction module, ImaGeNIe, in SMILE (Structural Modeling, Inference, and Learning Engine) and in GeNIe (SMILE's Windows user interface).