Visual Explainability

Machine learning methods use statistical learning to identify boundaries. One example of a machine learning method is a decision tree. A decision tree uses if-then statements to define patterns in data. In machine learning, these statements are called forks, and they split the data into two branches based on some value. That value between the branches is called a split point. A split point is the decision tree's version of a boundary. Every fork is adding information about data.

The distribution of the target variable based on some features refers to the way the values of the target variable (the variable being predicted) are spread out and grouped in relation to the values of one or more other features in the dataset. This information can give insights into the relationship between the target variable and the features, and help in building more accurate models.

For example, consider a dataset that contains information about marketing and sales. If the target variable is the ROAS, the distribution of the target variable based on the number of bedrooms could show how the average price of houses changes as the number of bedrooms increases or decreases. This information can be visualized in a plot, such as a bar graph or scatter plot, to make it easier to interpret.

Updated on: 02/02/2023