Scoring Metrics - Evaluating Machine Learning Models

Machine learning models can automate different kinds of processes --  prove customer creditworthiness, flag emails as spam, detect fraudulent transactions, forecast weather, optimize the electricity supply, and more! The overarching goal of all these applications is to have accurate predictions. But how do we define “accurate”?

This book explains different model evaluation - or scoring - techniques that show the model’s performance in a broader context, introducing the perspectives of single metrics and their robustness to the properties of data, and demonstrating the concrete value of a careful model validation.
 
The tool used to demonstrate the techniques is KNIME Analytics Platform.