Python: Scikit-learn

The accuracy of this model was .967. Although that is a good score, it could still be improved by using several different methods. The first, and possibly easiest, would be by using K-fold cross validation. This method separates a current dataset into k number of parts, called a fold. The algorithm is trained on k-1 folds with one held back and tested. This is repeated until each fold has been given the chance to be held back and tested. This method offers several performance scores that can be summarized using the mean or standard deviation. A variation of this method would be using repeated random test-train splits. This method offers some of the benefits of cross-validation, but since the same dataset is being used there can be some redundancy.