Deep learning of Value at Risk through generative neural network models : the case of the Variational Auto Encoder

Pierre Brugière (1) , Gabriel Turinici (1)

1 CEREMADE - CEntre de REcherches en MAthématiques de la DEcision

We present in this paper a method to compute, using generative neural networks, an estimator of the "Value at Risk" for a nancial asset. The method uses a Variational Auto Encoder with a 'energy' (a.k.a. Radon- Sobolev) kernel. The result behaves according to intuition and is in line with more classical methods.

Domaines: Intelligence artificielle [cs.AI]; Statistiques [math.ST]; Economies et finances

Pierre Brugière, Gabriel Turinici. Deep learning of Value at Risk through generative neural network models : the case of the Variational Auto Encoder. MethodX, 2023, 10, pp.102192. ⟨10.1016/j.mex.2023.102192⟩. ⟨hal-03880381⟩