arXiv Open Access 2025

Trading Graph Neural Network

Xian Wu

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

q-fin.TR cs.LG econ.GN q-fin.PR

Penulis (1)

Xian Wu

Format Sitasi

APA MLA BibTeX

Wu, X. (2025). Trading Graph Neural Network. https://arxiv.org/abs/2504.07923

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓