Neural Networks and Value at Risk

43 Pages Posted: 3 Jun 2020 Last revised: 11 Mar 2023

See all articles by Alexander Arimond

Alexander Arimond

University of Kaiserslautern - Sociovestix Labs - a DFKI spin-off

Damian Borth

University of St. Gallen - Institute of Computer Science

Andreas G. F. Hoepner

Smurfit Graduate Business School, University College Dublin; European Commission's Platform on Sustainable Finance

Michael Klawunn

Deutsche Factoring Bank GmbH & Co. KG

Stefan Weisheit

Talanx AG - HDI Global SE

Date Written: May 4, 2020

Abstract

Inspired by Gu, Kelly & Xiu’s (GKX, 2020) advancement of the measurement of asset risk premia via the introduction of feed forward neural networks, we investigate, if machine learning can advance the process of ‘estimating Value at Risk (VaR) thresholds’. For this purpose, we compare simple (GKX’s feed forward) and advanced (convolutional, recurrent) neural networks with established approaches (Hidden Markov Model, Mean/Variance). Utilizing a generative regime switching framework, we perform Monte-Carlo simulations of asset returns for Value at Risk threshold estimation. Using equity markets and long term bonds as test assets in the global, US, Euro area and UK setting over an up to 1,250 weeks sample horizon ending in August 2018, we investigate neural networks along three design steps relating (i) to the initialization of the neural network, (ii) its incentive function according to which it has been trained and (iii) the amount of data we feed. First, we compare neural networks with random seeding with networks that are initialized via estimations from the best-established model (i.e. the Hidden Markov). We find latter to outperform in terms of the frequency of VaR breaches (i.e. the realized return falling short of the estimated VaR threshold). Second, we balance the incentive structure of the loss function of our networks by adding a second objective to the training instructions so that the neural networks optimize for accuracy while also aiming to stay in empirically realistic regime distributions (i.e. bull vs. bear market frequencies). In particular this design feature enables the balanced incentive recurrent neural network (RNN) to outperform the single incentive RNN as well as any other neural network or established approach by statistically and economically significant levels. Third, we half our training data set of 2,000 days. We find our networks when fed with substantially less data (i.e. 1,000 days) to perform significantly worse which highlights a crucial weakness of neural networks in their dependence on very large data sets. Hence, we conclude that well designed neural networks, i.e. a recurrent neural network initialized with best current evidence and balanced incentives – can potentially advance the protection offered to institutional investors by VaR thresholds through a reduction in threshold breaches. However, such advancements rely on the availability of a long data history, which may not always be available in practice when estimating asset management VaR thresholds.

Keywords: Asset Management, Downside Risk, Initialization, Loss Function, Machine Learning, Neural Networks

JEL Classification: C01, C57, C58, G01, G17

Suggested Citation

Arimond, Alexander and Borth, Damian and Hoepner, Andreas G. F. and Klawunn, Michael and Weisheit, Stefan, Neural Networks and Value at Risk (May 4, 2020). Michael J. Brennan Irish Finance Working Paper Series Research Paper No. 20-7, Available at SSRN: https://ssrn.com/abstract=3591996 or http://dx.doi.org/10.2139/ssrn.3591996

Alexander Arimond

University of Kaiserslautern - Sociovestix Labs - a DFKI spin-off ( email )

Kaiserslautern, 67663
Germany

Damian Borth

University of St. Gallen - Institute of Computer Science ( email )

Dufourstrasse 40a
St. Gallen, CH-9000
Switzerland

HOME PAGE: http://https://cas-bdai.iwi.unisg.ch/main-lecturer/prof-damian-borth/

Andreas G. F. Hoepner (Contact Author)

Smurfit Graduate Business School, University College Dublin ( email )

Blackrock, Co. Dublin
Ireland

European Commission's Platform on Sustainable Finance ( email )

2 Rue de Spa
Brussels, 1000
Belgium

Michael Klawunn

Deutsche Factoring Bank GmbH & Co. KG ( email )

Langenstraße 15-21
Bremen, 28195
Germany

Stefan Weisheit

Talanx AG - HDI Global SE

HDI-Platz 1
Hannover, 30659
Germany

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
474
Abstract Views
2,331
Rank
101,532
PlumX Metrics