Neuro-evolutionary Decision Support System for Financial Time Series Analysis

Authors:
Piotr Lipinski
Affiliations:
Institute of Computer Science, University of Wroclaw, Wroclaw, Poland
Venue:
HAIS '08 Proceedings of the 3rd international workshop on Hybrid Artificial Intelligence Systems
Year:
2008

Citing 6
Cited 0

Original Contribution: A scaled conjugate gradient algorithm for fast supervised learning

Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Evolution Strategy in Portfolio Optimization

Selected Papers from the 5th European Conference on Artificial Evolution
Biologically Inspired Algorithms for Financial Modelling (Natural Computing Series)

Biologically Inspired Algorithms for Financial Modelling (Natural Computing Series)
Discovering stock market trading rules using multi-layer perceptrons

IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a hybrid decision support system for financial time series analysis. It uses evolutionary algorithms to construct an artificial expert, consisting of some expert rules, which processes financial time series and provides an expertise. Such expert rules are either static coming from the domain knowledge or are in the form of multi-layer perceptrons representing expert rules extracted from data.Results of a large number of experiments on real-life data from the Paris Stock Exchange confirm that the model of the hybrid decision support system is reasonable and it is able to generate reasonable solutions, not only over a training period, used in the training process, but also over a test period, unknown during constructing artificial experts.