mlsanityData to 7 Oct 2026

Scenario generation for market risk models using generative neural networks

arXiv 2109.10072 ↗First posted 21 Sep 2021cs.LG q-fin.MF q-fin.RMcited by 7

Not on the map. Why?

Abstract (arXiv)

In this research, we show how to expand existing approaches of using generative adversarial networks (GANs) as economic scenario generators (ESG) to a whole internal market risk model - with enough risk factors to model the full band-width of investments for an insurance company and for a one year time horizon as required in Solvency 2. We demonstrate that the results of a GAN-based internal model are similar to regulatory approved internal models in Europe. Therefore, GAN-based models can be seen as a data-driven alternative way of market risk modeling.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 22 of its 72 references that are in the map. First posted on arXiv 21 Sep 2021.

Builds on

22 of 72 references.

References · 22

  1. 2016Improved Techniques for Training GANscited by 2,938
  2. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  3. 2015A note on the evaluation of generative modelscited by 291
  4. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
  5. 2017Are GANs Created Equal? A Large-Scale Studycited by 267
  6. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  7. 2015On Wasserstein Two Sample Testing and Related Families of Nonparametric Testscited by 165
  8. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 107
  9. 2020The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabelingcited by 64
  10. 2018On GANs and GMMscited by 62
  11. 2018On Gradient-Based Learning in Continuous Gamescited by 46
  12. 2019Deep Hedging: Learning to Simulate Equity Option Marketscited by 25
10 more
  1. 2019Time Series Simulation by Conditional Generative Adversarial Netcited by 16
  2. 2019CorrGAN: Sampling Realistic Financial Correlation Matrices Using Generative Adversarial Networkscited by 15
  3. 2020Multivariate goodness-of-Fit tests based on Wasserstein distancecited by 11
  4. 2018Bayesian Renewables Scenario Generation via Deep Generative Networkscited by 7
  5. 2019Generative Synthesis of Insurance Datasetscited by 6
  6. 2020A Novel Framework for Selection of GANs for an Applicationcited by 5
  7. 2020Improving the Robustness of Trading Strategy Backtesting with Boltzmann Machines and Generative Adversarial Networkscited by 3
  8. 2016Multivariate goodness-of-fit on flat and curved spaces via nearest neighbor distancescited by 1
  9. 2018Generating virtual scenarios of multivariate financial data for quantitative trading applicationscited by 1
  10. 2020Synthesizing Property & Casualty Ratemaking Datasets using Generative Adversarial Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 5.

7 papers.

  1. 2025New Money: A Systematic Review of Synthetic Data Generation for Financecited by 5
  2. 2024Universal randomised signatures for generative time series modellingcited by 4
  3. 2025AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Modelscited by 3
  4. 2025Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarioscited by 1
  5. 2023Improved Data Generation for Enhanced Asset Allocation: A Synthetic Dataset Approach for the Fixed Income Universecited by 0
  6. 2025Batch normalization does not improve initializationcited by 0
  7. 2025LLM-Generated Counterfactual Stress Scenarios for Portfolio Risk Simulation via Hybrid Prompt-RAG Pipelinecited by 0