Modelling
And finally comes the time to actually start working: within the modeling phase, we try to get knowledge from our data, answering the questions we defined within the business understanding phase. The kind of model we are going to apply here will largely depend on the kind of data we will be dealing with, since every model has got data type and data distribution constraints.
What is relevant to understanding this phase is that it should not be considered a linear and sequential phase, but rather a cyclical one. To understand why, it will be sufficient to consider how it is usually performed, which is through the following three steps:
- Defining a data modeling strategy
- Model assumption evaluation
- Model assessment
Defining a data modeling strategy
In this step, starting from the exploratory analyses we have performed and the objectives we have declared within the business understanding phase, we start to limit the possible applicable models to a limited range, therefore defining our data...