Time Your Hedge With Deep Reinforcement Learning

@article{Benhamou2020TimeYH,
  title={Time Your Hedge With Deep Reinforcement Learning},
  author={E. Benhamou and David Saltiel and Sandrine Ungari and Abhishek Mukhopadhyay},
  journal={Libraries \& Information Technology eJournal},
  year={2020}
}
Can an asset manager plan the optimal timing for her/his hedging strategies given market conditions? The standard approach based on Markowitz or other more or less sophisticated financial rules aims to find the best portfolio allocation thanks to forecasted expected returns and risk but fails to fully relate market conditions to hedging strategies decision. In contrast, Deep Reinforcement Learning (DRL) can tackle this challenge by creating a dynamic dependency between market information and… 
AAMDRL: Augmented Asset Management With Deep Reinforcement Learning
TLDR
This paper illustrates how Deep Reinforcement Learning can tackle the challenge of learning efficiently in a noisy and self adapting environment with sequential, non-stationary and non-homogeneous observations through trading bots.
Is the Covid equity bubble rational? A machine learning answer
Is the Covid Equity bubble rational? In 2020, stock prices ballooned with S&P 500 gaining 16%, and the tech-heavy Nasdaq soaring to 43%, while fundamentals deteriorated with decreasing GDP forecasts,
Adaptive Supervised Learning for Volatility Targeting Models
TLDR
This work presents an innovative approach with an additional supervised learning step to predict the best model(s), based on historical performance ordering of RL models, and shows that adding a supervised learning overlay to decide which models to use provides improvement over a naive benchmark consisting in averaging all RL models.
Planning in Financial Markets in Presence of Spikes: Using Machine Learning GBDT
TLDR
A gradient boosting decision trees (GBDT) approach to predict large price drops in equity indexes from a set of 150 technical, fundamental and macroeconomic features and it is shown that retaining fewer and carefully selected features provides improvements across all ML approaches.
Explainable AI (XAI) Models Applied to Planning in Financial Markets
Regime changes planning in financial markets is well known to be hard to explain and interpret. Can an asset manager ex-plain clearly the intuition of his regime changes prediction on equity market ?
Explainable AI Models of Stock Crashes: A Machine-Learning Explanation of the Covid March 2020 Equity Meltdown
TLDR
A gradient boosting decision trees approach to predict large S&P 500 price drops from a set of 150 technical, fundamental and macroeconomic features is considered and it is shown that retaining fewer and carefully selected features provides improvements across all ML approaches.
Adaptive Learning for Financial Markets Mixing Model-Based and Model-Free RL for Volatility Targeting
TLDR
This work proposes to combine the best of the two techniques by selecting various model-based approaches thanks to Model-Free Deep Reinforcement Learning by using the traditional "walk-forward analysis", which is defined by successive training and testing based on expanding periods, to assert the robustness of the resulting agent.
Detecting and adapting to crisis pattern with context based Deep Reinforcement Learning
TLDR
This paper presents 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 that is able to detect and anticipate crisis like the current Covid one.
Bridging the Gap Between Markowitz Planning and Deep Reinforcement Learning
TLDR
This paper aims to bridge the gap between these two approaches to reinforcement learning by showing Deep Reinforcement Learning techniques can shed new lights on portfolio allocation thanks to a more general optimization setting that casts portfolio allocation as an optimal control problem that is not just a one-step optimization, but rather a continuous control optimization with a delayed reward.
...
...

References

SHOWING 1-10 OF 128 REFERENCES
Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States
TLDR
Experiments on two real-world datasets validate the effectiveness of SARL over existing PM approaches, both in terms of accumulated profits and risk-adjusted profits and extensive simulations are conducted to demonstrate the importance of the proposed state augmentation.
Model-based Deep Reinforcement Learning for Financial Portfolio Optimization
TLDR
This work designs a deep reinforcement learning (RL) architecture with an autonomous trading agent such that, given a portfolio, weight of assets in the portfolio are updated periodically, based on a global objective.
Optimistic Bull or Pessimistic Bear: Adaptive Deep Reinforcement Learning for Stock Portfolio Allocation
TLDR
A novel Adaptive Deep Deterministic Reinforcement Learning scheme (Adaptive DDPG) is proposed for the portfolio allocation task, which incorporates optimistic or pessimistic deep reinforcement learning that is reflected in the influence from prediction errors.
Detecting and adapting to crisis pattern with context based Deep Reinforcement Learning
TLDR
This paper presents 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 that is able to detect and anticipate crisis like the current Covid one.
Practical Deep Reinforcement Learning Approach for Stock Trading
TLDR
The proposed deep reinforcement learning approach is shown to outperform the two baselines in terms of both the Sharpe ratio and cumulative returns.
Adaptive Quantitative Trading: An Imitative Deep Reinforcement Learning Approach
TLDR
An adaptive trading model, namely iRDPG, is proposed, to automatically develop QT strategies by an intelligent trading agent and is enhanced by deep reinforcement learning (DRL) and imitation learning techniques.
Adversarial Deep Reinforcement Learning in Portfolio Management
TLDR
A so called Adversarial Training method is proposed and it can greatly improve the training efficiency and significantly promote average daily return and sharpe ratio in back test and results show that the agent based on Policy Gradient can outperform UCRP.
Cryptocurrency portfolio management with deep reinforcement learning
TLDR
This paper presents a model-less convolutional neural network with historic prices of a set of financial assets as its input, outputting portfolio weights of the set, trained with 0.7 years' price data from a cryptocurrency exchange.
Deep Learning for Finance: Deep Portfolios
TLDR
This work explores the use of deep learning hierarchical models for problems in financial prediction and classification and finds that deep learning can detect and exploit interactions in the data that are, at least currently, invisible to any existing financial economic theory.
...
...