Neural networks can detect model-free static arbitrage strategies

TL;DR

This paper shows that neural networks can effectively identify static arbitrage opportunities in financial markets, even with many securities, by solving complex convex semi-infinite programs.

Contribution

It introduces a method using neural networks to detect arbitrage opportunities in high-dimensional markets, supported by theoretical proofs and real data examples.

Findings

Neural networks can approximate solutions to convex semi-infinite programs.

The method is effective in high-dimensional market scenarios.

Real market data confirms the approach's robustness.

Abstract

In this paper we demonstrate both theoretically as well as numerically that neural networks can detect model-free static arbitrage opportunities whenever the market admits some. Due to the use of neural networks, our method can be applied to financial markets with a high number of traded securities and ensures almost immediate execution of the corresponding trading strategies. To demonstrate its tractability, effectiveness, and robustness we provide examples using real financial data. From a technical point of view, we prove that a single neural network can approximately solve a class of convex semi-infinite programs, which is the key result in order to derive our theoretical results that neural networks can detect model-free static arbitrage strategies whenever the financial market admits such opportunities.