Paper: arXiv 2602.19841

Authors: Krishna Neupane, Igor Griva, Robert Axtell, William Kennedy, Jason Kinser

Abstract

Corporate insiders trade for diverse reasons, often possessing Material Non-Public Information (MNPI). Determining whether specific trades leverage MNPI is a significant challenge due to inherent complexity. This study focuses on two critical objectives: accurately detecting Unlawful Insider Trading (UIT) and identifying key features explaining classification. The analysis demonstrates how combining Shapley Values (SHAP) and Causal Forest (CF) reveals these explanatory drivers. The findings underscore the necessity of causality in identifying and interpreting UIT, requiring the consideration of alternative scenarios and potential outcomes. Within a high-dimensional feature space, the proposed architecture integrates state-of-the-art techniques to achieve high classification accuracy. The framework provides robust feature rankings via SHAP and causal significance assessments through CF, facilitating the discovery of unique causal relationships. Statistically significant relationships are documented between the outcome and several key features, including director status, price-to-book ratio, return, and market beta. These features significantly influence the likelihood of UIT, suggesting potential links between insider behavior and factors such as information asymmetry, valuation risk, market volatility, and stock performance. The analysis draws attention to the complexities of financial causality, noting that while initial descriptors offer intuitive insights, deeper examination is required to understand nuanced impacts. These findings reaffirm the architectural flexibility of decision tree models. By incorporating heterogeneity during tree construction, these models effectively uncover latent structures within trade, finance, and governance data, characterizing fraudulent behavior while maintaining reliable results.

Complexity vs Empirical Score

  • Math Complexity: 5.5/10
  • Empirical Rigor: 6.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents a solid combination of predictive ML (XGBoost) and causal inference (Causal Forests, SHAP, AIPW) to detect and explain unlawful insider trading. While the underlying methods leverage established packages, applying causal inference to market microstructure and insider trade detection offers high empirical value and decent novel utility.

Research Flowchart

  flowchart TD
    A[Goal: Detect Unlawful Insider Trading & Identify Drivers] --> B[Input Data: Trade, Financial, & Governance Data]
    B --> C[Machine Learning Model Training]
    C --> D[SHAP Values: Feature Importance Ranking]
    C --> E[Causal Forest: Causal Relationship Assessment]
    D & E --> F[Key Drivers Identified: Director Status, P/B Ratio, Return, Market Beta]
    F --> G[Outcome: Robust UIT Detection & Causal Insights]