Trading Graph Neural Network

2025/04/10 by Xian Wu, Wu, Xian
Computer Science · #FOS: Computer and information sciences #FOS: Economics and business #General Economics (econ.GN) #Machine Learning (cs.LG) #Neural Networks and Applications #Pricing of Securities (q-fin.PR) #Trading and Market Microstructure (q-fin.TR)

paper · pdf · doi:10.48550/arxiv.2504.07923

openalex publication_date 2025/04/10 · openalex created_date 2025/10/01 · openalex updated_date 2026/07/28

Abstract

This paper proposes a new algorithm -- Trading Graph Neural Network (TGNN) that can structurally estimate the impact of asset features, dealer features and relationship features on asset prices in trading networks. It combines the strength of the traditional simulated method of moments (SMM) and recent machine learning techniques -- Graph Neural Network (GNN). It outperforms existing reduced-form methods with network centrality measures in prediction accuracy. The method can be used on networks with any structure, allowing for heterogeneity among both traders and assets.

Related

• Bellwether Trades: Characteristics of Trades influential in Predicting Future Price Movements in Markets
• GraphCNNpred: A stock market indices prediction using a Graph based deep learning system
• Price graphs: Utilizing the structural information of financial time series for stock prediction
• Forecasting Financial Market Structure from Network Features using Machine Learning
• Predict Forex Trend via Convolutional Neural Networks