Charting the predictive model's regression variables

Regression is a supervised learning algorithm. It needs five steps to be functional:

1. Build the regression model.
2. Check whether the cause variables have an effect on the dependent variable with statistical tests.
3. Train the model with a percentage of the dataset.
4. Test the model with the remainder of the dataset. See whether the results from the model fit the expected values of the dataset.
5. Finally, predict the values using the model.

The main target of a machine learning regression analysis is to build a model that predicts the value of interest (for example, sales of a product or plant growth in biology) based on a predictor variable (for example, marketing expenditure in the case of sales, or soil moisture in the plant growth scenario).

We need to find out whether the factor we want to predict has enough of a relationship with the variable we assume affects it. We have to prove that if...