Interaction techniques are used in ML and statistical modeling to capture the relationships between two or more features in a dataset for augmentation. The goal is to create new augmentation data that captures the interaction between existing components, which can help improve model performance and provide additional insights into the data. You can apply these techniques to cross-sectional or time-specific data, including normalizing, discretizing, and autoregression models.
Pluto has selected two out of seven methods for a hands-on Python programming demonstration. As with the transformation augmentation methods, the coding is repetitive. Thus, Pluto will provide fun challenges for the other five interaction augmentation techniques.
Pluto will start with the regression method, then the operator method.