We develop a 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 VaR estimates. The method is applied to daily and high-frequency returns of the S&P500 index over a period of 25 years.
- g17 - Financial Forecasting and Simulation
- c32 - "Multiple or Simultaneous Equation Models: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models"
- neural network
- volatility models
- equity returns
- risk management