Feature engineering

Feature engineering is the process of selecting and transforming the most relevant features in ML modeling. It is one of the most important steps in the ML learning process. Feature engineering includes feature selection and feature synthesis (transformation).

Feature selection

For an ML problem that has a lot of features extracted during the initial phase, feature selection is used to reduce the number of those features (input variables), so that we can focus on the features that are most useful to a model to predict the target variable. After you extract features for the problem, you need to use feature selection methods to choose the most appropriate features for model training. Depending on whether ML training is needed, there are two main types of feature selection methods you can use – filter methods and wrapper methods:

• Filter methods use statistical techniques to evaluate and score the relationship between each input variable and the...