Causal Inference in Finance: An Expertise-Driven Model for Instrument Variables Identification and Interpretation

TL;DR

This paper introduces an expertise-driven model for identifying and interpreting instrumental variables in finance, enhancing causal inference accuracy and interpretability using causal knowledge graphs and economic data.

Contribution

It proposes a novel expertise-based approach (ETE-FinCa) for IV construction and interpretation, addressing limitations of traditional synthetic IV methods in finance.

Findings

Feature selection with causal knowledge graphs improves classification accuracy by up to 11.7%.

High-quality IVs can identify causal relationships with statistical significance.

The model enhances interpretability of cause-effect relationships in financial data.

Abstract

Instrumental Variable (IV) provides a source of treatment randomization that is conditionally independent of the outcomes, responding to the challenges of counterfactual and confounding biases. In finance, IV construction typically relies on pre-designed synthetic IVs, with effectiveness measured by specific algorithms. This classic paradigm cannot be generalized to address broader issues that require more and specific IVs. Therefore, we propose an expertise-driven model (ETE-FinCa) to optimize the source of expertise, instantiate IVs by the expertise concept, and interpret the cause-effect relationship by integrating concept with real economic data. The results show that the feature selection based on causal knowledge graphs improves the classification performance than others, with up to a 11.7% increase in accuracy and a 23.0% increase in F1-score. Furthermore, the high-quality IVs we defined can identify causal relationships between the treatment and outcome variables in the Two-Stage Least Squares Regression model with statistical significance.