New Evolutionary Bankruptcy Forecasting Model Based on Genetic Algorithms and Neural Networks

Authors:
Trabelsi Abdelwahed;Esseghir Mohamed Amir
Affiliations:
BESTMOD Laboratory;BESTMOD Laboratory
Venue:
ICTAI '05 Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence
Year:
2005

Citing 0
Cited 4

An integrative model with subject weight based on neural network learning for bankruptcy prediction

Expert Systems with Applications: An International Journal
A hybrid approach based on the combination of variable selection using decision trees and case-based reasoning using the Mahalanobis distance: For bankruptcy prediction

Expert Systems with Applications: An International Journal
EGEA: a new hybrid approach towards extracting reduced generic association rule set (application to AML blood cancer therapy)

DaWaK'06 Proceedings of the 8th international conference on Data Warehousing and Knowledge Discovery
Differential evolution trained kernel principal component WNN and kernel binary quantile regression: Application to banking

Knowledge-Based Systems

Quantified Score

Hi-index	0.02

Visualization

Abstract

One of the problem still gaining a great attention in financeis the bankruptcy forecasts. The problem of efficient bankruptcy prognosis is of great interest both to scientists and practitioners. Numerous models have been developed to forecast bankruptcy prediction from statistical models to artificial intelligence techniques. We propose, in this study, a new hybrid model (EBM: Evolutionary Bankruptcy Model) based on genetic algorithms and artificial neural networks. Our evolutionary model is able of: selecting the best set of predictive variables, then, searching for the best neural network classifier and improving classification and generalization accuracies. Carried out experiments have shown a very promising results of EBM for bankruptcy prediction in terms of predictive accuracy and adaptability.