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

2025-11-11

International Conference on Data Technologies and Applications

AI Summary

This study addresses the challenge of detecting undetectable unlawful insider trading (UIT) in securities markets. We propose a supervised learning detection framework based on XGBoost, leveraging multi-dimensional trading behavior features—including temporal patterns, transaction size anomalies, and association with information windows—enhanced by domain-informed feature engineering and interpretability analysis. Evaluated on real-world insider trading data, the model achieves 97% classification accuracy, substantially outperforming conventional manual review and baseline models. Key contributions are: (1) a domain-adapted feature system specifically designed for UIT detection; (2) exploitation of XGBoost’s built-in feature importance to identify salient illicit behavioral patterns—e.g., concentrated pre-announcement purchases and abrupt position changes—thereby enhancing regulatory traceability; and (3) empirical validation of the framework’s high precision, computational efficiency, and strong interpretability in practical financial supervision.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Web Mining and Content Analysis: Bridging structured and unstructured data
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Security and Privacy: Data transparency and provenance

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.

Problem

• Detecting unlawful insider trading transactions using XGBoost
• Identifying fraudulent patterns in corporate securities trading
• Analyzing large-scale transaction data to uncover hidden illegal activities

Innovation

• XGBoost detects unlawful insider trading transactions
• Machine learning identifies fraudulent patterns with high accuracy
• Feature ranking highlights key indicators for fraud detection