© Hong Zhou 2020
H. ZhouLearn Data Mining Through Excelhttps://doi.org/10.1007/978-1-4842-5982-5_5

5. Cross-Validation and ROC

Hong Zhou1 
(1)
University of Saint Joseph, West Hartford, CT, USA
 

Please download the sample Excel files from https://github.com/hhohho/Learn-Data-Mining-through-Excel for this chapter’s exercises.

General Understanding of Cross-Validation

A prediction model should be validated before it can be successfully applied to scoring data. Using the same training dataset as the testing dataset to assess the constructed model is not a good way to validate the model. Such a validating strategy is called residual analysis. It compares the difference (so-called residual) between actual output and the predicted output. In Chapter 4, we ...

Get Learn Data Mining Through Excel: A Step-by-Step Approach for Understanding Machine Learning Methods now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.