Toward Automating Causal Discovery in Financial Markets and Beyond

This paper introduces a novel machine learning (ML) framework for causal discovery based on recent advances in large language models (LLMs) and discusses the applications of these causal discovery techniques to investment management. Unlike typical data-driven methods for data discovery, the framework using the implicit “world knowledge” in state-of-the-art LLMs to automate the expert judgment approach to causal discovery. A key application that is explored in detail is end-to-end causal factor analysis, where the authors demonstrate the utility of our method in specifying and analyzing detailed causal models for financial markets. This paper also conducts a comparative analysis, juxtaposing the new approach with conventional methods, to underscore the enhanced capability of the framework in revealing intricate causal dynamics in financial data.