Default prediction and Bankruptcy hazard analysis into recurent neuro-genetic hybrid networks to AdaBoost M1 regression and logistic regression models in finance

Authors:
Loukeris Nikolaos;Eleftheriadis Iordanis
Affiliations:
University of Macedonia and Polytechnic of Crete;University of Macedonia
Venue:
ICS'10 Proceedings of the 14th WSEAS international conference on Systems: part of the 14th WSEAS CSCC multiconference - Volume I
Year:
2010

Citing 3
Cited 0

Data mining: practical machine learning tools and techniques with Java implementations

Data mining: practical machine learning tools and techniques with Java implementations
Long Short-Term Memory

Neural Computation
Evolino: hybrid neuroevolution / optimal linear search for sequence learning

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Fund managers, and portfolio administrators must secure the net present value of their invested capital, providing an increasing return to investors. Regression models from the domain of Econometrics are used successfully in financial analysis, whilst Artificial Neural Networks and Genetic Algorithms in the field of Artificial Intelligence may offer significant results. A thorough comparison of additive model AdaBoost M1 regression, to various Logistic regression models such as: Logistic, Logit Boost, Simple Logistic, and hybrids of Recurrent neural networks optimized by Genetic Algorithms gives valuable information on the efficiency of these methods in Corporate Financial Analysis. Simple Logistic regression and Logistic Model Trees performed optimally.