5.6.7.4 Monthly Model Validation

  1. This pre-seeded batch will be available in all workspaces (production & sandboxes).
  2. This Batch is to be executed in the Production workspace.
  3. This Batch shows ongoing model drift and data quality with respect to new data every month (monthly).
Batch and Task Parameters

The batch contains a single task named Monthly_Model_Validation.

Task: Monthly_Model_Validation, Task Parameters
  • Objective folder for Data Quality :
    Home / Modeling / Pipelines / AIF Batch Framework / Supervised ML /
    Ongoing Model Validation / Monthly / Data Quality
  • Objective folder for Model Drift :
    Home / Modeling / Pipelines / AIF Batch Framework / Supervised ML /
    Ongoing Model Validation / Monthly / Model Drift
  • Do not change any parameter, except Optional Parameters.
  • Optional Parameters:
    • model_group_name: Name of the Model Groups for which Model has been trained. Example LOB1
    • model_group_scenario_name: Name of the Model Groups Scenario for which Model has been trained. Example Cash
    • osot_end_month: Specify the data month in YYYYMM format. If not specified by default latest month data available in the table will be picked up for monthly validations as scoring data / new data.
    • FEATURE_INCLUDE: List of features to be included for data quality. Default None means everything.
    • FEATURE_EXCLUDE: List of features to be excluded for data quality. Default None means exclude nothing.
      • When both include & exclude is provided. Include takes precedence over exclude.
      • Example 1 : feature_include="Feature1~Feature2"
      • Example 2 : feature_exclude="Feature3~Feature4~Feature5"
    • look_back_months: No of periods to look back for getting drift history. Default is 5.
    • Number_Of_Bins: Number of bins to be used in discretizing (scalar). Default is 9.
    • Boot_Strap_Samples: Number of bootstrap samples on which to estimate thresholds. Default is 5.
    • Standard_Deviation_Band_Sigma: Number of standard deviation band (sigma band). Threshold setting to be used. Default is 2 sigma.

    Example: model_group_name=LOB1,model_group_scenario_name=None,osot_end_month=No ne,Number_Of_Bins=9,Boot_Strap_Samples=5,Standard_Deviation_Band_Sigma=2,look_back_ months=5,FEATURE_INCLUDE=None,FEATURE_EXCLUDE=None

  • Optional Parameters can be edited from the Schedule Batch option.
  • Do not change any batch/task parameters, except Optional Parameters.