Graph Learning and Synthetic Positions for Options Statistical Arbitrage

Summary

This paper proposes a two-stage method for identifying and trading statistical arbitrage opportunities in options. First, it defines a prediction target intended to isolate pure arbitrage using synthetic bonds, then uses RNConv, a graph-learning architecture that incorporates a tree structure, to predict that target. The motivation includes the tabular nature of many features and the reported strength of tree-based methods on such data.

In the second stage, predictions are projected into synthetic long positions called SLSA. Under the paper’s arbitrage-free assumption, these positions are described as minimal risk and neutral to Black–Scholes risk factors. Experiments on KOSPI 200 index options report that RNConv outperforms graph-learning baselines and that SLSA produces positive returns, with a stated average P&L-contract information ratio of 0.1627. These results are specific to the reported dataset and assumptions; the summary does not establish performance in other options markets or under different trading costs and conditions.

Key ideas

• The method predicts an arbitrage-focused target defined using synthetic bonds.
• RNConv combines graph learning with a tree structure to handle the prediction task.
• The SLSA projection converts model predictions into synthetic long options positions.
• Under the arbitrage-free assumption, SLSA is described as minimal risk and neutral to Black–Scholes risk factors.
• Tests on KOSPI 200 options report baseline outperformance and positive SLSA returns, but broader generalization is not shown.

Tags

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


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









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.

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.