Nonstationary Continuum-Armed Bandit Strategies for Automated Trading in a Simulated Financial Market
This addresses the problem of automated trading for financial markets by providing an incremental improvement over existing adaptation methods.
The paper tackled the problem of designing an automated trading strategy that adapts to changing market conditions by framing it as a Nonstationary Continuum-Armed Bandit (NCAB) problem and proposing PRBO, a novel algorithm using Bayesian optimization and a bandit-over-bandit framework. Results showed that PRBO generated significantly more profit than the reference strategy PRSH in simulated financial markets.
We approach the problem of designing an automated trading strategy that can consistently profit by adapting to changing market conditions. This challenge can be framed as a Nonstationary Continuum-Armed Bandit (NCAB) problem. To solve the NCAB problem, we propose PRBO, a novel trading algorithm that uses Bayesian optimization and a ``bandit-over-bandit'' framework to dynamically adjust strategy parameters in response to market conditions. We use Bristol Stock Exchange (BSE) to simulate financial markets containing heterogeneous populations of automated trading agents and compare PRBO with PRSH, a reference trading strategy that adapts strategy parameters through stochastic hill-climbing. Results show that PRBO generates significantly more profit than PRSH, despite having fewer hyperparameters to tune. The code for PRBO and performing experiments is available online open-source (https://github.com/HarmoniaLeo/PRZI-Bayesian-Optimisation).