Detecting and adapting to crisis pattern with context based Deep Reinforcement Learning
This addresses the challenge of applying DRL to financial pattern detection and dis-investment for investors, though it appears incremental as it builds on existing DRL techniques with specific adaptations.
The paper tackles the problem of detecting and adapting to financial crises using deep reinforcement learning, achieving substantial outperformance over traditional portfolio optimization methods like Markowitz and demonstrating the ability to anticipate crises such as COVID-19.
Deep reinforcement learning (DRL) has reached super human levels in complex tasks like game solving (Go and autonomous driving). However, it remains an open question whether DRL can reach human level in applications to financial problems and in particular in detecting pattern crisis and consequently dis-investing. In this paper, we present an innovative DRL framework consisting in two sub-networks fed respectively with portfolio strategies past performances and standard deviations as well as additional contextual features. The second sub network plays an important role as it captures dependencies with common financial indicators features like risk aversion, economic surprise index and correlations between assets that allows taking into account context based information. We compare different network architectures either using layers of convolutions to reduce network's complexity or LSTM block to capture time dependency and whether previous allocations is important in the modeling. We also use adversarial training to make the final model more robust. Results on test set show this approach substantially over-performs traditional portfolio optimization methods like Markowitz and is able to detect and anticipate crisis like the current Covid one.