Level 1: Model (Advanced) Assessment

What type of information is stored in the Model Definition? Select all that apply.

True or False? Model Definition cannot be secured with roles.

True or False? The Model Definition and Materialized Database are separate entities; the materialized database can exist without the Model Definition.

Regardless of which Model interface is used, the underlying engine produces 3 main constructs; which one is only exposed in Model Pro?

Advanced users can construct a Master Flow which may contain multiple of the following; select all that apply.

A variable can be added to which of the following Data Flow nodes? Select all that apply.

In a Master Flow, a Pyramid Event can be used to execute a schedule for which of the following items? Select all that apply.

When we create an ML model, it is important to test it against data that was not used to train the model. The simplest way to achieve this is to divide our existing data into training and testing sets. What’s the best way in the Workflow to split the data between training and testing sets?

In a Prediction example, we use a Support Vector Machine model which only works against number inputs. What can we use to complete encoding columns and convert to numeric values?

True or False? You can save the output of a learn and predict algorithm as a machine learning model. This stores the existing results and allows you to add the ML model to another data flow later on.

When configuring a scripting node (Learn & Predict Script), what property determines the amount of data that is used to train the algorithm?

To create a Python “Learn & Predict Script” the script needs to contain which 3 of the following functions?

True or False? Using an existing ML Model node allows you to pass new data through a model you have already trained.

The ‘Learn and Predict Script’ algorithm can be added to a Python or R scripting node in which way?

True or False? The model score is evaluated after the algorithm has been run. To produce this score, the algorithm compares its predictions based on the training data with the actual data.