Enhancing classification and prediction using predictive modeling

摘要: In one embodiment, a system for enhancing predictive modeling includes an interface operable to receive first dataset. The may also include processor communicatively coupled the that is generate holdout dataset based on train each of plurality boosting models in parallel using dataset, wherein number iterations, training comprises: building one-level binary decision tree split-node variable; calculating impurity and optimal split node, node variable with lowest between models. then determine final model provides error rate when applied