Optimizing Returns Using the Hurst Exponent and Q Learning on Momentum and Mean Reversion Strategies

TL;DR

This paper explores combining the Hurst exponent with Q-learning to optimize momentum and mean reversion trading strategies, aiming to improve returns by classifying asset behavior and adapting trading decisions.

Contribution

It introduces a novel approach that uses the Hurst exponent to select trading strategies and applies Q-learning to enhance decision-making in financial trading.

Findings

Hurst exponent-based trading can increase average returns

Q-learning improves strategy adaptation and performance

Higher returns are achieved at the cost of increased risk

Abstract

Momentum and mean reversion trading strategies have opposite characteristics. The former is generally better with trending assets, and the latter is generally better with mean reverting assets. Using the Hurst exponent, which classifies time series as trending or mean reverting, we attempt to trade with each strategy when it is advantageous to generate higher returns on average. We ultimately find that trading with the Hurst exponent can achieve higher returns, but it also comes at a higher risk. Finally, we consider limitations of our study and propose a method using Q-learning to improve our strategy and implementation of individual algorithms.