2.0 now available

Open-Source Library for AI Model Explainability

Artificial intelligence can predict outcomes, but its inner workings can be a mystery. Facet, an open-source library by BCG X, cracks complex AI algorithms, uncovering how variables contribute to a model’s reasoning—and how you can get better results.

FACET hero

About Facet

Predictive AI is not a magic crystal ball. It’s based on science and has a long track record. But for many business leaders, the analogy does raise a point. Without understanding complex machine-learning (ML) algorithms, how can we truly trust the models—let alone base strategies upon them?

Facet, an open-source library by BCG X, takes a unique approach, showing how relevant features interact to determine key outcomes. This helps data scientists avoid common misinterpretations of ML models. And it reveals the variables that matter most. By explaining AI, Facet informs—and improves—decision making for both data science and the business.

Approach

How Facet Works

By analyzing patterns and making predictions, AI algorithms help advance everything from manufacturing efficiency to social impact. But as AI models become more complex, it is harder to understand how they arrive at their conclusions. That knowledge is crucial, for when you know what is driving a result, you know what to improve—and where to optimize—to get better results.

Facet delivers insights on the workings of AI in two ways:

Model inspection | FACET
1
Model Inspection

Model Inspection

Applying a unique geometric interpretation of ML models, Facet assesses how the variables interact; this transforms the explainability of ML models, as variables often act in a redundant or synergistic way. Understanding these dependencies has been difficult, leading to distorted interpretations of ML models. By uncovering these relationships, Facet reveals the true contributions of each variable.

Model Simulation | FACET
2
Model Simulation

Model Simulation

Once you know the critical variables and how they’re connected, you’re ready to optimize them. Facet's simulation algorithms let data scientists run what-if scenarios—virtual experiments to discover how changing key parameters affects predicted outcomes. By helping users identify the parameters that matter most, Facet provides a roadmap for achieving even better outcomes.

1
2
Model inspection | FACET
Model Simulation | FACET

Model Inspection

Applying a unique geometric interpretation of ML models, Facet assesses how the variables interact; this transforms the explainability of ML models, as variables often act in a redundant or synergistic way. Understanding these dependencies has been difficult, leading to distorted interpretations of ML models. By uncovering these relationships, Facet reveals the true contributions of each variable.

Model Simulation

Once you know the critical variables and how they’re connected, you’re ready to optimize them. Facet's simulation algorithms let data scientists run what-if scenarios—virtual experiments to discover how changing key parameters affects predicted outcomes. By helping users identify the parameters that matter most, Facet provides a roadmap for achieving even better outcomes.

Benefits

The Benefits of Understanding Complex ML Models

We designed Facet for easy use by data scientists. But the benefits extend across an organization. Chief among them:

Impact

Our Client’s Success with Facet

Our Experts

Meet Our Facet Team

Our experts work across industries—and around the world—to help organizations leverage the power of advanced analytics. Here are some of our experts on AI algorithms.

Jan Ittner

Jan Ittner

Partner and Director, Data Science

Munich

Ricardo Kennedy

Ricardo Kennedy

Principal - Data Science

Cologne

Mateusz Sokol

Mateusz Sokól

AI Software Engineer

Warsaw

FACET on GitHub

Visit Facet on Github

See our code and guide to get you up and running with Facet.

Find the Code

Explore Further

Explore Related Services

Tech + Us: Monthly insights for harnessing the full potential of AI and tech.