Generative Adversarial Networks in Finance: An Overview

@article{Eckerli2021GenerativeAN,
  title={Generative Adversarial Networks in Finance: An Overview},
  author={Florian Eckerli and Joerg Osterrieder},
  journal={Machine Learning eJournal},
  year={2021}
}
Modelling in finance is a challenging task: the data often has complex statistical properties and its inner workings are largely unknown. Deep learning algorithms are making progress in the field of data-driven modelling, but the lack of sufficient data to train these models is currently holding back several new applications. Generative Adversarial Networks (GANs) are a neural network architecture family that has achieved good results in image generation and is being successfully applied to… 

Deep Generators on Commodity Markets; application to Deep Hedging

TLDR
This article focuses on commodity markets and test four state-of-the-art generative methods, namely Time Series Generative Adversarial Network (GAN) Yoon et al.

Autoencoding Conditional GAN for Portfolio Allocation Diversification

TLDR
This paper introduces an autoencoding CGAN (ACGAN) based on deep generative models that learns the internal trend of historical data while modeling market uncertainty and future trends and shows that the proposed ACGAN model leads to better portfolio allocation and generates series that are closer to true data compared to the existing Markowitz and CGAN approaches.

PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series

TLDR
It is shown that PSA-GAN can be used to reduce the error in several downstream forecasting tasks over baselines that only use real data, and that Context-FID is indicative for downstream performance, and could be a useful tool to develop time series GAN models.

Generative Adversarial Networks: a systematic review and applications

TLDR
The most recent review papers are collected, the collected information is organized according to the application field and the application areas, the GAN architectures that have been applied in each case and the open issues in each area are summarized.

Editorial: Artificial intelligence in finance and industry: Highlights from 6 European COST conferences

COPYRIGHT © 2022 Henrici and Osterrieder. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in

Scale Dependencies and Self-Similarity Through Wavelet Scattering Covariance

TLDR
It is proved that self-similar processes have a scattering covariance matrix which is scale invariant, which provides non-Gaussian models of time-series having stationary increments and generates new time- series with a microcanonical sampling algorithm.

A Hybrid Approach on Conditional GAN for Portfolio Analysis

TLDR
This paper introduces a hybrid approach on conditional GAN based on deep generative models that learns the internal trend of historical data while mod-eling market uncertainty and future trends and shows that the proposed HybridCGAN and HybridACGAN models lead to better portfolio allocation compared to the existing Markowitz, CGAN, and ACGAN approaches.

GANs Training: A Game and Stochastic Control Approach

  • 2021

Scenario generation for market risk models using generative neural networks

TLDR
This research demonstrates that the results of a GAN-based ESG are similar to regulatory approved internal models in Europe and can be seen as an assumption-free data-driven alternative way of market risk modelling.

References

SHOWING 1-10 OF 41 REFERENCES

Enriching Financial Datasets with Generative Adversarial Networks

TLDR
This work wants to explore the generating capabilities of GANs applied to financial time series and investigate whether or not they can generate realistic financial scenarios.

Mitigating Overfitting on Financial Datasets with Generative Adversarial Networks

TLDR
A data augmentation technique using the Wasserstein GAN with gradient penalty is proposed and it is shown how training deep models on synthetic data mitigates overfitting, improving their performance on test data when compared to models trained solely on real data.

Conditional Sig-Wasserstein GANs for Time Series Generation

TLDR
A novel generator, called the conditional AR-FNN, is developed, designed to capture the temporal dependence of time series and can be efficiently trained, and consistently and significantly outperforms state-of-the-art benchmarks with respect to measures of similarity and predictive ability.

Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy.

TLDR
The objective is to provide an overview as well as a critical analysis of the status of GAN research in terms of relevant progress towards important computer vision application requirements.

Generative Adversarial Networks in Computer Vision

TLDR
The objective is to provide an overview as well as a critical analysis of the status of GAN research in terms of relevant progress toward critical computer vision application requirements and discuss the most compelling applications in computer vision.

Quant GANs: deep generation of financial time series

TLDR
Quant GANs is introduced, a data-driven model which is inspired by the recent success of generative adversarial networks (GANs), and results highlight that distributional properties for small and large lags are in an excellent agreement and dependence properties such as volatility clusters, leverage effects, and serial autocorrelations can be generated by the generator function of Quant GAns, demonstrably in high fidelity.

Self-Attention Generative Adversarial Networks

TLDR
The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset.

Time-series Generative Adversarial Networks

TLDR
A novel framework for generating realistic time-series data that combines the flexibility of the unsupervised paradigm with the control afforded by supervised training is proposed, which consistently and significantly outperforms state-of-the-art benchmarks with respect to measures of similarity and predictive ability.

Modeling financial time-series with generative adversarial networks

A generative adversarial network–based method for generating negative financial samples

TLDR
A new generation model, combined Generative Adversarial Network with Long Short-Term Memory network for one-dimensional negative financial samples, and a comprehensive evaluation method to evaluate the validity of generated samples from data distribution and attribute characteristics is defined.