Default Prediction and Bankruptcy Hazard Analysis into Recurent neuro-genetic hybrid networks to AdaBoost Ml Regression and Logistic Regression models in Finance

摘要

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 Ml 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.