Skip to content
Using Bidirectional Generative Adversarial Networks to estimate Value-at-Risk for Market Risk Management using Keras and TensorFlow.
Branch: master
Clone or download
Latest commit 1deb7cb Aug 18, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Markdown Final publish to Medium. Aug 18, 2018
Python Some edits. Aug 18, 2018
R Code edits. Aug 18, 2018
.gitignore Cleaned up market risk R code. Aug 7, 2018
LICENSE Initial commit Aug 6, 2018
README.md Update README.md Aug 14, 2018

README.md

Using Bidirectional Generative Adversarial Networks to estimate Value-at-Risk for Market Risk Management

We will explore the use of Bidirectional Generative Adversarial Networks (BiGAN) for market risk management: Estimation of portfolio risk measures such as Value-at-Risk (VaR). Generative Adversarial Networks (GAN) allow us to implicitly maximize the likelihood of a potentially complex distribution. Dealing with high dimensional data potentially coming from a complex distribution is a key aspect to market risk management among many other financial services use cases. GAN, specifically BiGAN, will allow us to deal with potentially complex financial services data such that we do not have to explicitly specify a distribution such as a multidimensional Gaussian distribution.

You can’t perform that action at this time.