Andrei Neagu

Outputs

Deep Hedging with Market Impact

Dynamic hedging is the practice of periodically transacting financial instruments to offset the risk caused by an investment or a liability. Dynamic hedging optimization can be framed as a sequential decision problem; thus, Reinforcement Learning (RL) models were recently proposed to tackle this task. However, existing RL works for hedging do not consider market impact caused by the finite liquidity of traded instruments. Integrating such a feature can be crucial to achieve optimal performance when hedging options on stocks with limited liquidity. In this paper, we propose a novel general market impact dynamic hedging model based on Deep Reinforcement Learning (DRL) that considers several realistic features such as convex market impacts, and impact persistence through time. The optimal policy obtained from the DRL model is analysed using several option hedging simulations and compared to commonly used procedures such as delta hedging. Results show our DRL model behaves better in contexts of low liquidity by, among others: 1) learning the extent to which portfolio rebalancing actions should be dampened or delayed to avoid high costs, 2) factoring in the impact of features not considered by conventional approaches, such as previous hedging errors through the portfolio value, and the underlying asset's drift (i.e. the magnitude of its expected return).

Deep Reinforcement Learning Algorithms for Financial Decision-Making

This research aims to develop a benchmarking framework for evaluating Deep Reinforcement Learning (DRL) algorithms in computational finance. Previous work often focuses on a single computational finance task and on a single DRL algorithm, limiting an objective comparison across both different computational finance tasks and different algorithms. Our work establishes a framework containing a variety of state-of-the-art DRL algorithms for a wide range of computational finance tasks and market environments, making objective comparisons more accessible to researchers. We address tasks such as option hedging and pricing, portfolio optimization, and optimal execution and use different classes of DRL algorithms such as policy-based, value-based and actor-critic methods. Our current work in progress focuses on policy-based DRL for option hedging with market impact, where transactions (buying and selling) affect market prices, providing a more realistic market environment than previously published works.