Robust decision support systems with matrix forecasts and shared layer perceptrons for finance and other applications

authored by: Hans Jörg Von Mettenheim, Michael H. Breitner
Abstract: The recent financial crisis showed the need for more robust decision support systems. In this paper, we introduce a novel type of recurrent artificial neural network, the shared layer perceptron, which allows forecasts that are robust by design. This is achieved by not over-fitting to a specific variable. An entire market is forecast. By training not one, but many networks, we obtain a distribution of outcomes. Further, multi-step forecasts are possible. Our system uses hidden states to model internal dynamics. This allows the network to build a memory and hardens it against external shocks. Using a single shared weight matrix offers the possibility of interpreting system output. An often cited disadvantage of neural networks, the black box character, is not an issue with our approach. We focus on two case studies: determining value at risk and transaction decision support. We also present other applications, including load forecast in electricity networks.
Organisation(s): Institute of Computer Science for Business Administration
Type: Conference contribution
Publication date: 2010
Publication status: Published
Peer reviewed: Yes
ASJC Scopus subject areas: Information Systems

BibTeX

@inproceedings{2ba270adad2a4425a155d32989f76269,
title = "Robust decision support systems with matrix forecasts and shared layer perceptrons for finance and other applications",
abstract = "The recent financial crisis showed the need for more robust decision support systems. In this paper, we introduce a novel type of recurrent artificial neural network, the shared layer perceptron, which allows forecasts that are robust by design. This is achieved by not over-fitting to a specific variable. An entire market is forecast. By training not one, but many networks, we obtain a distribution of outcomes. Further, multi-step forecasts are possible. Our system uses hidden states to model internal dynamics. This allows the network to build a memory and hardens it against external shocks. Using a single shared weight matrix offers the possibility of interpreting system output. An often cited disadvantage of neural networks, the black box character, is not an issue with our approach. We focus on two case studies: determining value at risk and transaction decision support. We also present other applications, including load forecast in electricity networks.",
keywords = "Artificial neural networks, Decision support systems (DSS), Financial forecast",
author = "{Von Mettenheim}, {Hans J{\"o}rg} and Breitner, {Michael H.}",
note = "Copyright: Copyright 2012 Elsevier B.V., All rights reserved.; 31st International Conference on Information Systems, ICIS 2010 ; Conference date: 12-12-2010 Through 15-12-2010",
year = "2010",
language = "English",
isbn = "9780615418988",
booktitle = "ICIS 2010 Proceedings",
}