Deep Reinforcement Learning (DRL) for Portfolio Allocation

• Published in: Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track Vol. 12461; pp. 527 - 531
• Main Authors: Benhamou, Eric, Saltiel, David, Ohana, Jean Jacques, Atif, Jamal, Laraki, Rida
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2021; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Convolutional networks; Deep reinforcement learning; Index surprise; Portfolio selection; Risk aversion
• ISBN: 9783030676698; 3030676692
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-67670-4_32

Deep reinforcement learning (DRL) has reached an unprecedent level on complex tasks like game solving (Go [6], StarCraft II [7]), and autonomous driving. However, applications to real financial assets are still largely unexplored and it remains an open question whether DRL can reach super human level. In this demo, we showcase state-of-the-art DRL methods for selecting portfolios according to financial environment, with a final network concatenating three individual networks using layers of convolutions to reduce network’s complexity. The multi entries of our network enables capturing dependencies from common financial indicators features like risk aversion, citigroup index surprise, portfolio specific features and previous portfolio allocations. Results on test set show this approach can overperform traditional portfolio optimization methods with results available at our demo website.