Saved in:
Bibliographic Details
Main Author: Wu, Xian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.07923
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910908525051904
author Wu, Xian
author_facet Wu, Xian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_07923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Trading Graph Neural Network
Wu, Xian
Trading and Market Microstructure
Machine Learning
General Economics
Economics
Pricing of Securities
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.
title Trading Graph Neural Network
topic Trading and Market Microstructure
Machine Learning
General Economics
Economics
Pricing of Securities
url https://arxiv.org/abs/2504.07923