Detecting Information Channels in Congressional Trading via Temporal Graph Learning

2026-02-05

AI Summary

This study addresses the identification of potential insider information channels and conflicts of interest in congressional stock trading. To this end, we construct a multimodal dynamic graph integrating heterogeneous data sources—including congressional trades, lobbying relationships, campaign contributions, and geographic affiliations—and propose a temporal graph network (TGN)-based framework for dynamic edge classification. Our approach incorporates risk-adjusted return labels and a two-stage forward-rolling validation mechanism to effectively mitigate look-ahead bias. This method represents the first systematic modeling of the temporal influence of dynamic interactions between Congress and corporations on trading performance. Over extended time horizons, it significantly identifies statistically meaningful instances of abnormal excess returns, thereby uncovering potential pathways through which informational advantages may flow.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Information Extraction

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Congressional stock trading has raised concerns about potential information asymmetries and conflicts of interest in financial markets. We introduce a temporal graph network (TGN) framework to identify information channels through which members of Congress may possess advantageous knowledge when trading company stocks. We construct a multimodal dynamic graph integrating diverse publicly available datasets, including congressional stock transactions, lobbying relationships, campaign finance contributions, and geographical connections between legislators and corporations. Our approach formulates the detection problem as a dynamic edge classification task, where we identify trades that exhibit statistically significant outperformance relative to the S&P 500 across long time horizons. To handle the temporal nature of these relationships, we develop a two-step walk-forward validation architecture that respects information availability constraints and prevents look-ahead bias. We evaluate several labeling strategies based on risk-adjusted returns and demonstrate that the TGN successfully captures complex temporal dependencies between congressional-corporate interactions and subsequent trading performance.

Problem

• information asymmetry
• congressional trading
• temporal graph learning
• financial markets
• insider advantage

Innovation

• Temporal Graph Network
• Dynamic Edge Classification
• Look-ahead Bias Prevention
• Multimodal Dynamic Graph
• Congressional Trading