Deep Hedging: Hedging Derivatives Under Generic Market Frictions Using Reinforcement Learning

Buehler, Hans; Gonon, Lukas; Teichmann, Josef; Wood, B. Dan; Mohan, Baranidharan; Kochems, Jonathan

doi:10.2139/ssrn.3355706

Cited by 45 publications

(49 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reward function 𝑟 (𝑠, 𝑎, 𝑠 ′ ) is the incentive for an agent to learn a better policy. FinRL supports user-defined reward functions to reflect risk-aversion or market friction [6,54] and provides commonly used ones [13] as follows:…”

Section: Application Layermentioning

confidence: 99%

FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance

et al. 2021

View full text Add to dashboard Cite

Deep reinforcement learning (DRL) has been envisioned to have a competitive edge in quantitative finance. However, there is a steep development curve for quantitative traders to obtain an agent that automatically positions to win in the market, namely to decide where to trade, at what price and what quantity, due to the error-prone programming and arduous debugging. In this paper, we present the first open-source framework FinRL as a full pipeline to help quantitative traders overcome the steep learning curve. FinRL is featured with simplicity, applicability and extensibility under the key principles, full-stack framework, customization, reproducibility and hands-on tutoring.Embodied as a three-layer architecture with modular structures, FinRL implements fine-tuned state-of-the-art DRL algorithms and common reward functions, while alleviating the debugging workloads. Thus, we help users pipeline the strategy design at a high turnover rate. At multiple levels of time granularity, FinRL simulates various markets as training environments using historical data and live trading APIs. Being highly extensible, FinRL reserves a set of user-import interfaces and incorporates trading constraints such as market friction, market liquidity and investor's risk-aversion. Moreover, serving as practitioners' stepping stones, typical trading tasks are provided as step-by-step tutorials, e.g., stock trading, portfolio allocation, cryptocurrency trading, etc. CCS CONCEPTS• Computing methodologies → Machine learning; Markov decision processes; Reinforcement learning.

show abstract

Section: Application Layermentioning

confidence: 99%

FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance

et al. 2021

View full text Add to dashboard Cite

show abstract

“…More recently, Buehler et al [2019a,b] and Ruf and Wang [2020] follow up on this line of research. Buehler et al [2019b] consider also the hedging of exotic options such as barrier options.…”

Section: Outputsmentioning

confidence: 99%

Neural networks for option pricing and hedging: a literature review

Ruf¹,

Wang²

2020

JCF

View full text Add to dashboard Cite

Neural networks have been used as a nonparametric method for option pricing and hedging since the early 1990s. Far over a hundred papers have been published on this topic. This note intends to provide a comprehensive review. Papers are compared in terms of input features, output variables, benchmark models, performance measures, data partition methods, and underlying assets. Furthermore, related work and regularisation techniques are discussed.

show abstract

“…• Max Pooling Layer: For a given pooling size p, the max pooling layer returns a vector whose entries are the maximum among the neighbouring p entries in the feature map. For example, for feature map (1, 3, 8, 2, 1, 0, 0, 4, 6, 1) and p = 3 the max pooling output is (8,8,8,8,8,2,4,6,6,6).…”

Section: A Artificial Neural Networkmentioning

confidence: 99%

“…Neural networks provide a powerful way of identifying relationships between input parameters and model output and can be particularly useful for models that do not have closed-form solution [27,28]. Recent work found that neural network calibration framework can be successfully applied to a range of rough stochastic volatility models to aid accurate pricing and hedging [6,28] The aim of this paper was to conduct an exploratory empirical study examining the volatility of fMRI noise. We were specifically interested in exploring whether volatility of fMRI noise exhibits time-dependent behaviour that cannot be explained by factors such as head motion and physiological noise.…”

Section: Introductionmentioning

confidence: 99%

Sailing in rough waters: examining volatility of fMRI noise

Leppänen

Stone

Lythgoe

et al. 2020

Preprint

View full text Add to dashboard Cite

1.AbstractBackgroundFunctional resonance magnetic imaging (fMRI) noise is usually assumed to have constant volatility. However this assumption has been recently challenged in a few studies examining heteroscedasticity arising from head motion and physiological noise. However, to our knowledge no studies have studied heteroscedasticity in scanner noise. Thus the aim of this study was to estimate the smoothness of fMRI scanner noise using latest methods from the field of financial mathematics.MethodsA multi-echo fMRI scan was performed on a phantom using two 3 tesla MRI units. The echo times were used as intra-time point data to estimate realised volatility. Smoothness of the realised volatility processes is examined by estimating the Hurst parameter, a parameter H ∈ (0, 1) governing the roughness (Hölder continuity) of paths in the rough Bergomi model, introduced in [2]. The rough Bergomi model a member of the family of rough stochastic volatility models. A family of models which was recently popularised in mathematical finance by observations indicating that volatility in financial markets is best described by stochastic models where volatility can be modulated by the Hurst parameter H, which usually calibrates to values H ∈ (0, 0.5) (the rough case), hence inspiring the name of the model family. In this work, calibration of the Hurst parameter H is performed pathwise, using recently developed neural network calibration tools.ResultsIn all experiments the volatility calibrates to values well within the rough case H < 0.5 and on average fMRI scanner noise was very rough with H ≈ 0.03. Substantial variability was also observed, which was caused by edge effects, whereby H was larger near the edges of the phantoms.DiscussionThe findings challenge the assumption that fMRI scanner noise has constant volatility (in fact, the lower the value of H, the more pronounced the oscillations of the volatility, and hence the more “severe” is the violation of the constant volatility assumption) and add to the steady accumulation of studies suggesting implementing methods to model heteroscedasticity may improve fMRI data analysis. Additionally, the present findings add to previous work showing that the mean and normality of fMRI noise processes show edge effects, such that signal near the edges of the images is less likely to meet the assumptions of current modelling methods.

show abstract

Deep Hedging: Hedging Derivatives Under Generic Market Frictions Using Reinforcement Learning

Cited by 45 publications

References 14 publications

FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance

FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance

Neural networks for option pricing and hedging: a literature review

Sailing in rough waters: examining volatility of fMRI noise

Contact Info

Product

Resources

About