Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Predicting Exchange Rate Value-at-Risk and Expected Shortfall: A Neural Network Approach

Bijelic, Anna LU and Ouijjane, Tilila (2019) NEKN02 20191
Department of Economics
Abstract
On the basis of the recommendation of the Basel Committee on Banking Supervision to transition from Value-at-Risk (VaR) to Expected Shortfall (ES) in determining market risk capital, this paper attempts to investigate whether a Recurrent Neural Network provides more accurate VaR and ES predictions of the EUR/USD exchange rate compared to the conventional GARCH(1,1) model. A number of previous studies has confirmed the forecasting ability of a plain vanilla Feedforward Neural Network over traditional statistical models. However, standard neural networks have limitations. Most notably, they rely on the assumption of independency among data observations, which presents a problem when data points are related in time. To circumvent this... (More)
On the basis of the recommendation of the Basel Committee on Banking Supervision to transition from Value-at-Risk (VaR) to Expected Shortfall (ES) in determining market risk capital, this paper attempts to investigate whether a Recurrent Neural Network provides more accurate VaR and ES predictions of the EUR/USD exchange rate compared to the conventional GARCH(1,1) model. A number of previous studies has confirmed the forecasting ability of a plain vanilla Feedforward Neural Network over traditional statistical models. However, standard neural networks have limitations. Most notably, they rely on the assumption of independency among data observations, which presents a problem when data points are related in time. To circumvent this restriction, this study employs a Gated Recurrent Unit type of neural network to produce one-step-ahead volatility forecasts of the EUR/USD exchange rate, which are then used to compute VaR and ES predictions. The VaR and ES forecasts for both models are obtained through a Volatility Weighted Historical Simulation, and evaluated with backtesting procedures. The empirical results indicate that the GARCH(1,1) model outperforms the Gated Recurrent Unit neural network for VaR95%, while the Gated Recurrent Unit neural network appears more adequate in forecasting ES at a 95% confidence level. (Less)
Please use this url to cite or link to this publication:
author
Bijelic, Anna LU and Ouijjane, Tilila
supervisor
organization
course
NEKN02 20191
year
type
H1 - Master's Degree (One Year)
subject
keywords
Value-at-Risk, Expected Shortfall, Recurrent Neural Networks, GRU, GARCH(1, 1), Exchange Rate Volatility, Intra-day Data
language
English
id
8989138
date added to LUP
2019-08-08 10:30:25
date last changed
2019-08-08 10:30:25
@misc{8989138,
  abstract     = {{On the basis of the recommendation of the Basel Committee on Banking Supervision to transition from Value-at-Risk (VaR) to Expected Shortfall (ES) in determining market risk capital, this paper attempts to investigate whether a Recurrent Neural Network provides more accurate VaR and ES predictions of the EUR/USD exchange rate compared to the conventional GARCH(1,1) model. A number of previous studies has confirmed the forecasting ability of a plain vanilla Feedforward Neural Network over traditional statistical models. However, standard neural networks have limitations. Most notably, they rely on the assumption of independency among data observations, which presents a problem when data points are related in time. To circumvent this restriction, this study employs a Gated Recurrent Unit type of neural network to produce one-step-ahead volatility forecasts of the EUR/USD exchange rate, which are then used to compute VaR and ES predictions. The VaR and ES forecasts for both models are obtained through a Volatility Weighted Historical Simulation, and evaluated with backtesting procedures. The empirical results indicate that the GARCH(1,1) model outperforms the Gated Recurrent Unit neural network for VaR95%, while the Gated Recurrent Unit neural network appears more adequate in forecasting ES at a 95% confidence level.}},
  author       = {{Bijelic, Anna and Ouijjane, Tilila}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Predicting Exchange Rate Value-at-Risk and Expected Shortfall: A Neural Network Approach}},
  year         = {{2019}},
}