用图神经网络分析交易网络中资产、交易员及关系对价格的影响
Trading Graph Neural Network
- 结合经典方法与图神经网络，建模交易网络结构
- 预测准确率优于传统中心性度量方法
- 适用于异质性交易员和资产的任意网络结构
本文提出一种新算法——交易图神经网络（TGNN），可结构化估计资产特征、交易员特征及关系特征对资产价格的影响。该方法融合传统模拟矩方法（SMM）与近期机器学习技术——图神经网络（GNN）。相比基于网络中心性度量的现有简化模型，其预测准确率显著提升。该方法适用于任意结构的交易网络，支持交易员与资产之间的异质性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。