Mapa mental
REPTREE CLASSIFIERS FOR CREDIT RISK FORECAST
Contenido del mapa
REPTREE CLASSIFIERS FOR CREDIT RISK FORECAST
- Tree based classifiers are easier to interpret and explain
fast decision tree learning algorithm
based on the principle of computing the information gain with entropy and minimizing the error arising from variance
- applies regression tree logic and generates multiple trees in altered iterations
- picks best one from all spawned trees
- constructs the regression/decision tree using variance and information gain
- prunes the tree using reduced-error pruning with back fitting method
- constructs the regression/decision tree using variance and information gain
- picks best one from all spawned trees
- applies regression tree logic and generates multiple trees in altered iterations
Información
- Descripción
- Graduate diploma (Data Mining) Graduate Diploma in Computing Mapa Mental sobre REPTREE CLASSIFIERS FOR CREDIT RISK FORECAST, creado por Freda Fung el 04/11/2016.
- Creado por
- Freda Fung
- Visitas
- 3
- Valoración
Más sobre Decision Trees and Ensemble Learning