Scholarlink

<p>Changes in the prices of multiple financial assets over time can be characterized by their complex nature and interdependence. More traditional forecasting approaches may overlook the interdependencies among these assets, since they may not fully consider the spatial-temporal dependencies between them. Graph neural networks&#xa0;(GNNs) have emerged as powerful tools for modeling complex relational dependencies in areas such as social network analysis and traffic forecasting. However, their application in asset price prediction remains relatively unexplored. Here, we investigate GNNs’ effectiveness in forecasting multiple financial asset prices jointly, specifically in the foreign exchange&#xa0;(Forex) and cryptocurrency markets. We employ three spatio-temporal GNN frameworks-MTGNN, StemGNN, and FourierGNN-which are all recognized for their state-of-the-art performance in forecasting multivariate time series. These models transform time-series data into graphs and capture both spatial and temporal dependencies. They significantly outperform the baseline methods, including LSTM, ARIMA, and VAR, in predicting financial asset prices in the highly volatile cryptocurrency market. While the performance gap is less obvious in the relatively stable Forex market, GNN-based models still demonstrate a general advantage over LSTM, although they are outperformed by ARIMA. Through a series of experiments and backtesting strategies, we assess the predictive power and profitability of these models in portfolio construction. Our code and datasets are publicly available at <a href="https://github.com/seferlab/">https://github.com/seferlab/temporal gnn</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Financial asset price prediction with graph neural network-based temporal deep learning models

  • 期刊论文

  • 发表日期：

    2025年9月8日

查看全文
  • Yasin Uygun,
  • Emre Sefer

摘要

Changes in the prices of multiple financial assets over time can be characterized by their complex nature and interdependence. More traditional forecasting approaches may overlook the interdependencies among these assets, since they may not fully consider the spatial-temporal dependencies between them. Graph neural networks (GNNs) have emerged as powerful tools for modeling complex relational dependencies in areas such as social network analysis and traffic forecasting. However, their application in asset price prediction remains relatively unexplored. Here, we investigate GNNs’ effectiveness in forecasting multiple financial asset prices jointly, specifically in the foreign exchange (Forex) and cryptocurrency markets. We employ three spatio-temporal GNN frameworks-MTGNN, StemGNN, and FourierGNN-which are all recognized for their state-of-the-art performance in forecasting multivariate time series. These models transform time-series data into graphs and capture both spatial and temporal dependencies. They significantly outperform the baseline methods, including LSTM, ARIMA, and VAR, in predicting financial asset prices in the highly volatile cryptocurrency market. While the performance gap is less obvious in the relatively stable Forex market, GNN-based models still demonstrate a general advantage over LSTM, although they are outperformed by ARIMA. Through a series of experiments and backtesting strategies, we assess the predictive power and profitability of these models in portfolio construction. Our code and datasets are publicly available at https://github.com/seferlab/temporal gnn.