Statistical Arbitrage in Options Markets by Graph Learning and Synthetic Long Positions

2025-08-20

AI Summary

This paper addresses the underutilization of graph-structured information in statistical arbitrage for equity options, where tabular features dominate existing approaches. To mitigate model sensitivity to pricing errors, we first construct synthetic bonds to define a pure arbitrage prediction objective. Second, we propose RNConv—a hybrid architecture integrating tree-based inductive bias with graph convolution—and introduce SLSA (Synthetic Linear Statistical Arbitrage), a theoretically risk-free position formulation with a projection-based transformation mechanism, executed robustly via Black–Scholes risk-neutral hedging. Empirical evaluation on KOSPI 200 index options demonstrates that RNConv significantly outperforms mainstream baselines; the SLSA strategy achieves an average information ratio of 0.1627 per contract, with consistently positive returns. These results validate the effectiveness and novelty of integrating graph learning with structured arbitrage design in options markets.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Game Theory and Economic Paradigms: Adversarial Learning
• Search and Optimization: Learning to Search

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

Statistical arbitrages (StatArbs) driven by machine learning has garnered considerable attention in both academia and industry. Nevertheless, deep-learning (DL) approaches to directly exploit StatArbs in options markets remain largely unexplored. Moreover, prior graph learning (GL) -- a methodological basis of this paper -- studies overlooked that features are tabular in many cases and that tree-based methods outperform DL on numerous tabular datasets. To bridge these gaps, we propose a two-stage GL approach for direct identification and exploitation of StatArbs in options markets. In the first stage, we define a novel prediction target isolating pure arbitrages via synthetic bonds. To predict the target, we develop RNConv, a GL architecture incorporating a tree structure. In the second stage, we propose SLSA -- a class of positions comprising pure arbitrage opportunities. It is provably of minimal risk and neutral to all Black-Scholes risk factors under the arbitrage-free assumption. We also present the SLSA projection converting predictions into SLSA positions. Our experiments on KOSPI 200 index options show that RNConv statistically significantly outperforms GL baselines, and that SLSA consistently yields positive returns, achieving an average P&L-contract information ratio of 0.1627. Our approach offers a novel perspective on the prediction target and strategy for exploiting StatArbs in options markets through the lens of DL, in conjunction with a pioneering tree-based GL.

Problem

• Directly exploiting statistical arbitrage in options markets using deep learning
• Bridging the gap between graph learning and tabular data performance
• Developing minimal-risk synthetic positions neutral to Black-Scholes factors

Innovation

• Graph learning with tree-based architecture
• Synthetic long positions for arbitrage
• Two-stage approach combining prediction and strategy