An extreme Gradient Boosting (XGBoost) Trees approach to Detect and Identify Unlawful Insider Trading (UIT) Transactions

Paper: arXiv 2511.08306

Authors: Krishna Neupane, Igor Griva

Abstract

Corporate insiders have control of material non-public preferential information (MNPI). Occasionally, the insiders strategically bypass legal and regulatory safeguards to exploit MNPI in their execution of securities trading. Due to a large volume of transactions a detection of unlawful insider trading becomes an arduous task for humans to examine and identify underlying patterns from the insider’s behavior. On the other hand, innovative machine learning architectures have shown promising results for analyzing large-scale and complex data with hidden patterns. One such popular technique is eXtreme Gradient Boosting (XGBoost), the state-of-the-arts supervised classifier. We, hence, resort to and apply XGBoost to alleviate challenges of identification and detection of unlawful activities. The results demonstrate that XGBoost can identify unlawful transactions with a high accuracy of 97 percent and can provide ranking of the features that play the most important role in detecting fraudulent activities.

Complexity vs Empirical Score

• Math Complexity: 2.5/10
• Empirical Rigor: 4.0/10
• Quadrant: Philosophers — conceptual discussion, limited math and data

Why this score: The paper primarily applies a known machine learning classifier (XGBoost) without developing novel mathematics, resulting in low math complexity; while it reports high accuracy (97%) on a large dataset, the absence of full backtesting details, transaction costs, or live implementation details places it in a conceptual rather than ready-for-deployment space.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Detect Unlawful Insider Trading"] --> B["Input: Financial &<br>Insider Transaction Data"]
  B --> C["Method: XGBoost<br>Supervised Learning Model"]
  C --> D["Computational Process:<br>Training & Pattern Recognition"]
  D --> E{"Model Validation<br>& Testing"}
  E -- Iterative Tuning --> C
  E --> F["Key Findings:<br>97% Accuracy in Detection"]
  F --> G["Outcome:<br>Ranked Feature Importance<br>for Fraud Identification"]

Cited References (867)

1. Analysis of runoff generation driving factors based on hydrological model and interpretable machine learning method (2022)
2. Research on personal credit risk evaluation based on XGBoost (2022)
3. A novel XGBoost extension for credit scoring class-imbalanced data combining a generalized extreme value link and a modified focal loss function (2022)
4. Anomaly detection using XGBoost ensemble of deep neural network models (2021)
5. Customer transaction fraud detection using xgboost model (2020)
6. HMMPred: Accurate Prediction of DNA-Binding Proteins Based on HMM Profiles and XGBoost Feature Selection (2020)
7. Principal Component Analysis and the Cross-Sectional Variation of Returns (2021)
8. A Random Forest approach to detect and identify Unlawful Insider Trading — → 2411.13564

1 of 867 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.