4. Model Execution Routine

Refer to the “Pre-requisites” prior to proceeding with the next section.

This is the second step to be executed. It is assumed that model building routine mentioned in the previous section is already processed.

This chapter contains the following sections:

• Section 4.1, "Contextual Information"
• Section 4.2, "Model Execution"

4.1 Contextual Information

As part of this process, data will be refreshed as of the current date. The customer attrition model that has been built in the previous step will be loaded and executed. As part of this routine the customer life time value and segmentation models will get built and executed runtime.

4.2 Model Execution

User(s)

It is suggested that only the FLEXCUBE user with admin rights should have access to the model execution screens

Launch ‘Model Execution and Control’ screen from the menu

Machine Learning Retail -> Model Administration -> Model Execution and Control

.

Select "Model Execute" radio button

Data Fields	Remarks
Period Start Date	Will get defaulted to 12 months prior to Period End date. User can modify.
Period End Date	Will get defaulted to the latest date across branches. Not allowed to modify
Attrition Date	Will get defaulted to Period End date. Not allowed to modify
Silent Period to consider for attrition identification	Will get defaulted to 180 days. Not allowed to modify

Suggestions:

 

• PERIOD START DATE and PERIOD END DATE to cover a span of 12 Months

Process ‘Model Execute’ routine

Click ‘Process’ button to trigger model execution.

Periodic Model Execution

 

• Model execution frequency will be decided by business

Note

• Model execution time may extend from several minutes to few hours
• Built Models are re-used each time the data is refreshed