Business Models (“Evergreen Production Model Inventory”)
Clicking the “Business Models” from the main menu opens the Evergreen Model Inventory (sometimes referred by others as “Production Model Inventory”). The production model inventory contains the full list of registered models within ModelOp Center, regardless of the model type, model factory in which it was produced, current state of the model (registered vs. in QA vs. deployed).
Search. A user may search for a model by Name or Tag by using the Search bar:
Filter. A user can filter the models based on the filter categories on the right:
See Model Details. A user may click on any row to view the specific details of that model (see subsequent “Model Details” page):
Compare Models. Additionally, to compare one or more models, a user may select “Enable champion challenger” toggle button. This will expose the “Champion/Challenger” column, allowing the user compare two or models models using the “Champion/Challenger” check boxes. Champion/Challenger is an industry standard technique to compare the performance of competing model strategies, or the performance of a recently updated model against a previous version of the same model.
To compare 2 or more models (Champion/Challenger):
This section describes the Champion/Challenger feature in ModelOp Center, and how to use it to help determine the best model method or approach to promote to production.
Table of Contents
Introduction
Data Science requires experimentation using a variety of methods, approaches, frameworks, and potentially even coding languages. While most data scientists will conduct their experimentation in their model development environment, data scientists--and the managerial and governance reviewers--often want to review that a candidate model for production performs better than any currently running version of the model. The Champion/Challenger feature in ModelOp Center presents a side-by side comparison of the performance of different models--or versions of the same model--to help users analyze which model or model version is best suited for production usage.
The following phases lay the groundwork for doing a Champion/Challenger comparison.
Define the evaluation metrics for the model. See Model Monitoring: Overview.
Automate evaluation tests - this is done either by manually running metrics jobs (see Running a Metrics Job Manually) or through an automated MLC Process. You can build an MLC Process to automatically execute metrics tests for a particular version of a model. See Model Lifecycle Management Overview for more information.
Conduct a side-by-side comparison of the test results in the Champion/Challenger page of the Command Center (see next section).
Champion/Challenger Comparison
For the previously generated metrics results (see steps 1 & 2 above), use the following steps to activate the Champion/Challenger feature in the ModelOp Center to compare test results side-by-side.
Within the Evergreen Production Model Inventory, enable the “Enable champion challenger” toggle button. This will expose the “Champion/Challenger” column, allowing the user compare two or models models using the “Champion/Challenger” check boxes.
2. Hit the “Compare Models” button
3. The Champion/Challenger comparison screen will open to compare the latest Test Results for those selected models
See Model Governance: Model Management for more information about the information that is contained for each model within the Production Model Inventory.
Next Article: Model Monitoring: Overview >
See Model Governance: Standard Model Definition for more information about the information that is contained for each model within the Production Model Inventory.
Next Article: Model Governance: Interpretability >