A Neural Network with Shared Dynamics for Multi‐Step Prediction of Value‐at‐Risk and Volatility

We develop a Long Short-Term Memory (LSTM) neural network for the joint prediction of volatility, realized volatility and Value-at-Risk. Regularization by means of pooling the dynamic structure for the different outputs of the models is shown to be a powerful method for improving forecasts and smoothing Value-at-Risk (VaR) estimates. The method is applied to daily and high-frequency returns of the S&P500 index over a period of 25 years.

Netspar, Network for Studies on Pensions, Aging and Retirement, is een denktank en kennisnetwerk. Netspar is gericht op een goed geïnformeerd pensioendebat.

MEER OVER NETSPAR


Missie en strategie           •           Netwerk           •           Organisatie           •          Podcasts
Board Brief            •            Werkprogramma 2023-2027           •           Onderzoeksagenda

OVER NETSPAR

Onze partners

vu
NN_logo_gray
B20190901_nidi-logo_greyscale
B20160708_apg
B20160708_ministeries
Bekijk al onze partners