Deep Reinforcement Learning for Cryptocurrency Trading: Practical Approach to Address Backtest Overfitting
This addresses the reliability of trading strategies for cryptocurrency investors by mitigating overfitting, though it is incremental as it builds on existing DRL methods.
The paper tackles the problem of backtest overfitting in deep reinforcement learning for cryptocurrency trading by proposing a hypothesis test to detect and reject overfitted agents, showing that less overfitted agents achieve higher returns than overfitted ones, an equal weight strategy, and the S&P DBM Index during a testing period with market crashes.
Designing profitable and reliable trading strategies is challenging in the highly volatile cryptocurrency market. Existing works applied deep reinforcement learning methods and optimistically reported increased profits in backtesting, which may suffer from the false positive issue due to overfitting. In this paper, we propose a practical approach to address backtest overfitting for cryptocurrency trading using deep reinforcement learning. First, we formulate the detection of backtest overfitting as a hypothesis test. Then, we train the DRL agents, estimate the probability of overfitting, and reject the overfitted agents, increasing the chance of good trading performance. Finally, on 10 cryptocurrencies over a testing period from 05/01/2022 to 06/27/2022 (during which the crypto market crashed two times), we show that the less overfitted deep reinforcement learning agents have a higher return than that of more overfitted agents, an equal weight strategy, and the S&P DBM Index (market benchmark), offering confidence in possible deployment to a real market.