Signature Optimal Stopping for Statistical Arbitrage Entry and Exit

Summary

This paper develops a method for timing both entry into and liquidation of positions in mean-reverting price spreads. It frames the decisions as sequential optimal stopping problems and explicitly includes transaction costs. A refined signature-based optimal stopping method is used to identify when to open a position and when to close it, without requiring a predefined model for the spread dynamics.

Numerical results are reported as evidence that the framework performs better than conventional mean-reversion rules. The supplied description does not specify the spread universe, transaction-cost assumptions, evaluation design, or size of the performance difference. Its model flexibility is a stated feature, but the evidence summarized here is not sufficient to determine how results transfer to live trading or to other assets and market conditions.

Key ideas

• Entry and liquidation are treated as sequential optimal stopping decisions.
• The framework incorporates transaction costs when choosing the timing of trades.
• A signature-based method is used without specifying a fixed model for spread dynamics.
• Numerical comparisons favor the method over conventional mean-reversion rules, though evaluation details are not given.

Tags

# Optimal Entry and Exit with Signature in Statistical Arbitrage


# Optimal Entry and Exit with Signature in Statistical Arbitrage









In this paper, we explore an optimal timing strategy for the trading of price spreads exhibiting mean-reverting characteristics. A sequential optimal stopping framework is formulated to analyze the optimal timings for both entering and subsequently liquidating positions, all while considering the impact of transaction costs. Then we leverages a refined signature optimal stopping method to resolve this sequential optimal stopping problem, thereby unveiling the precise entry and exit timings that maximize gains. Our framework operates without any predefined assumptions regarding the dynamics of the underlying mean-reverting spreads, offering adaptability to diverse scenarios. Numerical results are provided to demonstrate its superior performance when comparing with conventional mean reversion trading rules.

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.