Graph Learning for Foreign Exchange Rate Prediction and Statistical Arbitrage

2025-08-20

AI Summary

This paper addresses two critical bottlenecks in foreign exchange rate prediction (FXRP): (1) the absence of graph learning methods capable of modeling multi-currency interactions and exchange-rate–interest-rate coupling, and (2) the neglect of temporal latency between price observation and trade execution. We propose the first two-stage graph learning framework for FXRP. First, we construct a spatiotemporal heterogeneous graph that explicitly encodes currency nodes and directed edges representing exchange rates and interest rates, and design an edge-level regression model for dynamic forecasting. Second, we introduce a time-lag-aware stochastic optimization module that enforces statistical arbitrage under empirical arbitrage constraints. Theoretical analysis establishes no-arbitrage consistency. Empirical results demonstrate significant improvements: mean squared error (MSE) of predictions is substantially reduced; information ratio of the resulting arbitrage strategy increases by 61.89%; and Sortino ratio improves by 45.51%.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Social networks and social learning

Abstract

We propose a two-step graph learning approach for foreign exchange statistical arbitrages (FXSAs), addressing two key gaps in prior studies: the absence of graph-learning methods for foreign exchange rate prediction (FXRP) that leverage multi-currency and currency-interest rate relationships, and the disregard of the time lag between price observation and trade execution. In the first step, to capture complex multi-currency and currency-interest rate relationships, we formulate FXRP as an edge-level regression problem on a discrete-time spatiotemporal graph. This graph consists of currencies as nodes and exchanges as edges, with interest rates and foreign exchange rates serving as node and edge features, respectively. We then introduce a graph-learning method that leverages the spatiotemporal graph to address the FXRP problem. In the second step, we present a stochastic optimization problem to exploit FXSAs while accounting for the observation-execution time lag. To address this problem, we propose a graph-learning method that enforces constraints through projection and ReLU, maximizes risk-adjusted return by leveraging a graph with exchanges as nodes and influence relationships as edges, and utilizes the predictions from the FXRP method for the constraint parameters and node features. Moreover, we prove that our FXSA method satisfies empirical arbitrage constraints. The experimental results demonstrate that our FXRP method yields statistically significant improvements in mean squared error, and that the FXSA method achieves a 61.89% higher information ratio and a 45.51% higher Sortino ratio than a benchmark. Our approach provides a novel perspective on FXRP and FXSA within the context of graph learning.

Problem

• Leveraging multi-currency and interest rate relationships for FX prediction
• Addressing time lag between price observation and trade execution
• Formulating statistical arbitrage as stochastic optimization with constraints

Innovation

• Graph-learning for multi-currency and interest rate relationships
• Stochastic optimization with time lag constraints
• Edge-level regression on spatiotemporal exchange graphs