Skip to content
All library documents

Graph Learning for FX Prediction and Execution-Aware Statistical Arbitrage

Article arXiv papers · Author: Yoonsik Hong et al.
Read the original

Summary

The proposed approach combines foreign exchange rate prediction with statistical arbitrage while accounting for the delay between observing prices and executing trades. Its first stage models exchange-rate prediction as edge-level regression on a discrete-time spatiotemporal graph: currencies are nodes, exchange rates are edge features, and interest rates contribute node features. This structure is intended to represent relationships across currencies and rates.

The second stage formulates arbitrage as a stochastic optimization problem. A graph of exchanges and their influence relationships supports risk-adjusted portfolio decisions, while projection and ReLU enforce constraints using the prediction model's outputs. The authors report statistically significant mean squared error improvements for prediction and higher information and Sortino ratios than a benchmark for arbitrage, as well as a proof of empirical arbitrage constraints. The supplied description does not specify the data, benchmark construction, or evaluation period, so the reported gains cannot be assessed for broader market applicability from this text alone.

Key ideas

  • FX prediction is modeled as edge-level regression on a spatiotemporal graph of currencies and exchanges.
  • Interest rates and exchange rates enter the graph as node and edge features, respectively.
  • The arbitrage stage explicitly accounts for the time lag between observing prices and executing trades.
  • Projection and ReLU are used to enforce constraints in a stochastic optimization framework.
  • The authors report prediction error improvements and higher risk-adjusted metrics than a benchmark.

Tags

ForexArbitrageMachine learningStatisticsExecution
Full text
# Graph Learning for Foreign Exchange Rate Prediction and Statistical Arbitrage


# Graph Learning for Foreign Exchange Rate Prediction and Statistical Arbitrage









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.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.