Multivariate Pair Trading by Volatility & Model Adaption Trade-off

TL;DR

This paper introduces VMAT, a novel strategy for multivariate pair trading that balances volatility and model adaptation, demonstrating superior profitability over existing methods.

Contribution

The paper proposes a simple, profitable multivariate pair trading strategy called VMAT, addressing the gap in portfolio management for multivariate time series.

Findings

VMAT outperforms baseline strategies in profit.

Experimental results confirm the effectiveness of VMAT.

The approach balances volatility and model adaptation for better trading outcomes.

Abstract

Pair trading is one of the most discussed topics among financial researches. Despite a growing base of work, portfolio management for multivariate time series is rarely discussed. On the other hand, most researches focus on refining strategy rules instead of finding the optimal portfolio weight. In this paper, we brought up a simple yet profitable strategy called Volatility & Model Adaption Trade-off (VMAT) to leverage the issues. Experiment studies show its superior profit performance over baselines.