CTMSTOU driven markets: simulated environment for regime-awareness in trading policies

TL;DR

This paper introduces a novel simulation environment for studying regime-aware trading policies using a new stochastic process, CTMSTOU, to model fundamental values in regime-switching markets.

Contribution

The paper presents the CTMSTOU process and demonstrates its use in a simulated environment to analyze trading strategies in regime-aware markets.

Findings

Regime-aware trading strategies outperform non-aware ones in simulated markets.

The CTMSTOU process effectively models regime switching in fundamental values.

Explicit regime switching improves order execution performance.

Abstract

Market regimes is a popular topic in quantitative finance even though there is little consensus on the details of how they should be defined. They arise as a feature both in financial market prediction problems and financial market task performing problems. In this work we use discrete event time multi-agent market simulation to freely experiment in a reproducible and understandable environment where regimes can be explicitly switched and enforced. We introduce a novel stochastic process to model the fundamental value perceived by market participants: Continuous-Time Markov Switching Trending Ornstein-Uhlenbeck (CTMSTOU), which facilitates the study of trading policies in regime switching markets. We define the notion of regime-awareness for a trading agent as well and illustrate its importance through the study of different order placement strategies in the context of order execution problems.