Ensemble machine learning algorithm optimization of bankruptcy prediction of bank

The ensemble consists of a single set individually trained models, the predictions which are combined when classifying new cases, in building good classification model requires diversity model. algorithm, logistic regression, support vector machine, random forest, and neural network models as alternative sources information. Previous research has shown that ensembles more accurate than models. Single modified bagging some techniques we will study this paper. We experimented with banking industry’s financial ratios. results his observations are: First, an is always Second, observe show improved performance on balanced datasets, they can adjust behavior make them suitable for relatively small datasets. accuracy rate 97% learning model, increase level up to 16% compared other use unbalanced