The authors propose models for the solution of the fundamental problem of option replication subject to discrete trading, round lotting, and nonlinear transaction costs using state-of-the-art methods in deep reinforcement learning (DRL), including deep Q-learning, deep Q-learning with Pop-Art, and proximal policy optimization (PPO). Each DRL model is trained to hedge a whole range of strikes, and no retraining is needed when the user changes to another strike within the range. The models are general, allowing the user to plug in any option pricing and simulation library and then train them with no further modifications to hedge arbitrary option portfolios. Through a series of simulations, the authors show that the DRL models learn similar or better strategies as compared to delta hedging. Out of all models, PPO performs the best in terms of profit and loss, training time, and amount of data needed for training. TOPICS:Big data/machine learning, options, risk management, simulations Key Findings • The authors propose models for the replication of options over a whole range of strikes subject to discrete trading, round lotting, and nonlinear transaction costs based on state-of-the-art methods in deep reinforcement learning including deep Q-learning and proximal policy optimization. • The models allow the user to plug in any option pricing and simulation library and then train them with no further modifications to hedge arbitrary option portfolios. • A series of simulations demonstrates that the deep reinforcement learning models learn similar or better strategies as compared to delta hedging. • Proximal policy optimization outperforms the other models in terms of profit and loss, training time, and amount of data needed for training.
21 December 2006 in Communications in Mathematical Physics
We prove general reflection positivity results on Riemannian manifolds for both scalar fields and Dirac fields, and comment on applications to quantum field theory. As another application, we prove the inequality between Dirichlet and Neumann covariance operators on a manifold with a reflection.
In multi-period trading with realistic market impact, determining the dynamic trading strategy that optimizes expected utility of final wealth is a hard problem. In this paper we show that, with an appropriate choice of the reward function, reinforcement learning techniques (specifically, Q-learning) can successfully handle the risk-averse case. We provide a proof of concept in the form of a simulated market which permits a statistical arbitrage even with trading costs. The Q-learning agent finds and exploits this arbitrage.
19 February 2021 in The Journal of Portfolio Management
The Black–Litterman model is one of the most popular models in quantitative finance, with numerous theoretical and practical achievements. From the standpoint of investment theory, the Black–Litterman model allows seamless incorporation of Bayesian statistics into the portfolio optimization process. From a practical standpoint, it provides portfolio managers with a structured approach to express subjective views, thereby freeing their investment processes from a total reliance on backward-looking historical data. In this article, the authors provide an overview of the original Black–Litterman model and its various extensions and enhancements addressing issues in real-world trading and investment management. TOPICS:Quantitative methods, statistical methods, portfolio construction, performance measurement Key Findings ▪ The authors provide an overview of the original Black–Litterman model and its various extensions and enhancements, addressing issues in real-world trading and investment management. ▪ Many important practical considerations in implementing the Black-Litterman model are discussed including choice of priors, view generation, and transaction costs. ▪ Particular emphasis is given to the extensions of the Black-Litterman model of significant practical relevance to today’s investors such as factor models, model misspecification, non-normality, and multiperiod portfolio optimization.