Introduction

After conducting stress testing, users may uncover various scenarios where models fail, posing significant business continuity risks. Additionally, each business typically has specific guidelines they wish to enforce on models. In AryaXAI, these guidelines are defined as 'Policies'.

Policies serve as rules or guidelines that can override model predictions. The framework implements these policies on the models, adhering to the instructions provided by the user.

When a policy is executed for a case, ‘Model Prediction’ is the original model prediction and ‘Final prediction’ is the overridden prediction based on the custom rules defined.

Create policies

To create a new policy:

If decision = custom text as the output, then use 'input' and add your text message in the 'input'.

project.create_policy(policy_name='Low FICO',expression="(fico_range_high < 300)",statement="This case has abnormally low fico score. It is {fico_range_high}",decision='1')

Help function to create a new policy:

help(project.create_policy)

Manage Policies

Delete policy

project.delete_policy()

Viewing risk policies

View policies for a project

project.policies()