Tree-Based Machine Learning Methods in SAS Viya

Chapter 9: Additional Gradient Boosting Models

Gradient Boosting for Transfer Learning

Some data mining and machine learning applications have only a scarce amount of training data available, pictorially represented in Figure 9.1. In addition, we make a basic assumption that the training and the test data have the same distribution. Nevertheless, in many cases, this identical distribution assumption does not hold. The assumption might be violated when a task from one new domain comes, while there are only labeled data from a similar old domain. Labeling the new data can be costly, and it would also be a waste to throw away all the old data.

For example, insurance providers do not label many claims as fraudulent or non-fraudulent. Web mining is ...