Perform generalized linear regression to generate predictions, or to model the relationship of a dependent variable to a set of explanatory variables. Identifying and measuring relationships can lead to a better understanding of what is happening in a place, a prediction that something might happen in a place, or an investigation into why something happened in the place where it happened. The regression model extends the distribution of dependent variable to exponential distribution (Gaussian distribution, Bernoulli distribution, Poisson distribution), and can deal with the regression analysis of some common discrete and continuous random variables, especially the attribute data and discrete data. It has advantages in solving the problem of discontinuous and non-numerical variables.

The data Training Procedure of the generalized linear regression method can be used to obtain the corresponding model according to the data characteristics, and then used for prediction.

When creating a generalized linear regression training task, you need to set the following parameters:

 

After executing the training task, the following Result Parameter is output: