Extended Sample 5: Train, Test, Evaluate for Binary Classification with Multiple Algorithms

March 24, 2015
This experiment demonstrates how we can build a binary classification model to predict income levels of adult individuals. The process includes training, testing and evaluating two models on the Adult dataset.
This is an extended version of sample 5, showing how multiple algorithms can be compared. In this case, the boosted decision tree performs better than the logistic regression model. Sample 5 details are here: http://gallery.azureml.net/Details/3fe213e3ae6244c5ac84a73e1b451dc4 Created by a Microsoft employee.