ValidMind Library

Published

May 12, 2025

The ValidMind Library helps you streamline model documentation by automating the generation of drafts. All you need to do is upload your documentation artifacts and test results to the ValidMind Platform.

What is the ValidMind Library?

The ValidMind Library provides a rich collection of documentation tools and test suites, from documenting descriptions of your dataset to validation testing your models for weak spots and overfit areas.

ValidMind offers two primary methods for automating model documentation:

Generate documentation¹ — Through automation, the library extracts metadata from associated datasets and models for you and generates model documentation based on a template. You can also add more documentation and tests manually using the documentation editing capabilities in the ValidMind Platform.
Run validation tests² — The library provides a suite of validation tests for common financial services use cases. For cases where these tests do not cover everything you need, you can also extend existing test suites with your own proprietary tests or testing providers.

¹ ValidMind for model development

² ValidMind for model validation

The ValidMind Library is designed to be model agnostic. If your model is built in Python, the library provides all the standard functionality you may need without requiring you to rewrite any functions.

Key ValidMind concepts

model documentation: A structured and detailed record pertaining to a model, encompassing key components such as its underlying assumptions, methodologies, data sources, inputs, performance metrics, evaluations, limitations, and intended uses.

Within the realm of model risk management, this documentation serves to ensure transparency, adherence to regulatory requirements, and a clear understanding of potential risks associated with the model's application.

validation report: A formal document produced after a model validation process, outlining the findings, assessments, and recommendations related to a specific model's performance, appropriateness, and limitations. Provides a comprehensive review of the model's conceptual framework, data sources and integrity, calibration methods, and performance outcomes.

Within model risk management, the validation report is crucial for ensuring transparency, demonstrating regulatory compliance, and offering actionable insights for model refinement or adjustments.

template, documentation template: Functions as a test suite and lays out the structure of model documentation, segmented into various sections and sub-sections. Documentation templates define the structure of your model documentation, specifying the tests that should be run, and how the results should be displayed.

ValidMind templates come with pre-defined sections, similar to test placeholders, including boilerplates and spaces designated for documentation and test results. When rendered, produces a document that model developers can use for model validation.

test: A function contained in the library, designed to run a specific quantitative test on the dataset or model. Test results are sent to the ValidMind Platform to generate the model documentation according to the template that is associated with the documentation.

Tests are the building blocks of ValidMind, used to evaluate and document models and datasets, and can be run individually or as part of a suite defined by your model documentation template.

metrics, custom metrics: Metrics are a subset of tests that do not have thresholds. Custom metrics are functions that you define to evaluate your model or dataset. These functions can be registered via the ValidMind Library to be used with the ValidMind Platform.

In the context of ValidMind's Jupyter Notebooks, metrics and tests can be thought of as interchangeable concepts.

inputs: Objects to be evaluated and documented in the ValidMind Library. They can be any of the following:

model: A single model that has been initialized in ValidMind with vm.init_model(). See the Model Documentation or the for more information.
dataset: Single dataset that has been initialized in ValidMind with vm.init_dataset(). See the Dataset Documentation for more information.
models: A list of ValidMind models - usually this is used when you want to compare multiple models in your custom tests.
datasets: A list of ValidMind datasets - usually this is used when you want to compare multiple datasets in your custom tests. (Learn more: [Run tests with multiple datasets(/notebooks/how_to/run_tests_that_require_multiple_datasets.ipynb)])

parameters: Additional arguments that can be passed when running a ValidMind test, used to pass additional information to a test, customize its behavior, or provide additional context.
outputs: Custom tests can return elements like tables or plots. Tables may be a list of dictionaries (each representing a row) or a pandas DataFrame. Plots may be matplotlib or plotly figures.
test suite: A collection of tests which are run together to generate model documentation end-to-end for specific use cases.

For example, the classifier_full_suite test suite runs tests from the tabular_dataset and classifier test suites to fully document the data and model sections for binary classification model use cases.

QuickStart

After you sign up for ValidMind to get access, try our QuickStart:

Quickstart for model documentation

Welcome! Let's get you started with the basic process of documenting models with ValidMind.

ValidMind QuickStart

Watch the walkthrough on YouTube: https://youtu.be/rIR8Mql7eGs

ValidMind for model development

Learn how to use ValidMind for your end-to-end model documentation process based on common model development scenarios with our ValidMind for model development series of four introductory notebooks:

1 — Set up the ValidMind Library

Get to know ValidMind by setting up the ValidMind Library in your own environment, and registering a sample binary classification model in the ValidMind Platform for use with this series of notebooks.

2 — Start the model development process

Learn to run and log tests with a variety of methods and in different situations with the ValidMind Library, then add the results or evidence to your documentation for the sample model you registered.

3 — Integrate custom tests

After you become familiar with the basics of the ValidMind Library, learn how to supplement ValidMind tests with your own and include them as additional evidence in your documentation.

4 — Finalize testing and documentation

Wrap up by learning how to ensure that custom tests are included in your model's documentation template. By the end of this series, you will have a fully documented sample model ready for review.

ValidMind for model validation

Learn how to use ValidMind for your end-to-end model validation process based on common scenarios with our ValidMind for model validation series of four introductory notebooks:

1 — Set up the ValidMind Library for validation

Get to know ValidMind by setting up the ValidMind Library in your own environment, and gaining access as a validator to a sample model in the ValidMind Platform for use with this series of notebooks.

2 — Start the model validation process

Independently verify the data quality tests performed on datasets used to train the dummy champion model using tests from the ValidMind Library, then add the results or evidence to your validation report.

3 — Developing a potential challenger model

After you become familiar with the basics of the ValidMind Library, use it to develop a potential challenger model and run thorough model comparison tests, such as performance, diagnostic, and feature importance tests.

4 — Finalize validation and reporting

Wrap up by learning how to include custom tests and verifying that all tests conducted during model development were run and reported accurately. By the end of this series, you will have a validation report complete with findings ready for review.

Learn how to run tests

The ValidMind Library provides many built-in tests and test suites which make it easy for developers to automate their model documentation. Start by running a pre-made test, then modify it, and finally create your own test:

Run tests & test suites