January 24th, 2019

What is Your AI Thinking? Part 2

RSS icon RSS Category: Data Science, Driverless AI, Explainable AI, Financial Services, Machine Learning Interpretability
Fallback Featured Image

Explaining AI to the Business Person

Welcome to part 2 of our blog series: What is Your AI Thinking? We will explore some of the most promising testing methods for enhancing trust in AI and machine learning models and systems. We will also cover the best practice of model documentation from a business and regulatory standpoint.

More Techniques

Model Debugging and Sensitivity Analysis

Understanding and trust are intrinsically linked, and ideally we want to both trust and understand any deployed AI system. While explanatory techniques are mostly about increasing understanding of AI and machine learning models and systems, model debugging is about enhancing trust in those same systems by testing them in real-life and simulated scenarios. Sensitivity analysis, also known as scenario analysis or “what-if” analysis, is probably the best-known method for testing the behavior of machine learning models.

Sensitivity Analysis – How will your model behave in the next market boom or bust? What if it encounters data it never learned about during its training process? Is it easy to hack or game the AI system you’ve created? Sensitivity analysis helps provide answers to all of these questions the old-fashioned way: by testing these scenarios explicitly. In sensitivity analysis, data is generated that replicates a scenario of interest: a recession, unseen data, or a hacking attempt, and then model behavior on this data is analyzed. If your model is not passing these tests in a way you are comfortable with, send yourself or your team back to the drawing board!

Fairness and Disparate Impact Analysis

Sociological fairness in machine learning is an incredibly important, but highly complex subject. In a real-world machine learning project the hard-to-define phenomena of unfairness can materialize in many ways and from many different sources. However, there is a practical way to discuss and handle observational fairness, or how your model predictions affect different groups of people. This is known as disparate impact analysis.

Disparate Impact Analysis – Disparate impact analysis is a fairly straightforward method that quantifies your model’s predictions across sensitive demographic segments like ethnicity, gender, disability status or other potentially interesting groups of observations. Disparate impact analysis is also an accepted, regulation-compliant tool for fair-lending purposes in the U.S. financial services industry. If it’s good enough for multibillion-dollar credit portfolios, it’s probably good enough for your project! Also, why risk being called out in the media for training an unfair model? And why not do the right thing and investigate how your model treats people?

Tie It all Together with Model Documentation

Along with a strong global and local understanding of your model and data, trust in its future behavior, and assurances of fairness, model interpretability is also about minimizing financial risk. Large financial services companies have been calculating and documenting information similar to that described above with this goal in mind for years.

Model Documentation – Model documentation is required in some industries but represents a best practice for all. Documentation should include essential information about machine learning models including:

  • The creation date and creator of the model
  • The model’s intended business purpose
  • A description of the input dataset
  • Description of the algorithm(s) used for: Data preparation and model training
  • Final model tuning parameters
  • Model validation steps
  • Results from explanatory techniques
  • Results from disparate impact analysis
  • Results from sensitivity analysis
  • Who to contact when a model causes problems
  • Ideas about how to fix any potential problems

All of this information can be given to a data scientist, internal validators, or external regulators to understand precisely how the model was generated and what to do if it ever causes problems.

Interpretable models, explanations, model debugging, fairness techniques and model documentation are being pursued by researchers and software vendors…today! In Part 3 of this blog series learn how to use H2O Driverless AI to get a jump on your competition by automatically building low-risk, high-accuracy, and high-interpretability machine learning models.

This blog is second in a 3-part series. You can catch the first part here and the third part here.

About the Author

patrick hall
Patrick Hall

Patrick Hall is a senior director for data science products at H2O.ai where he focuses mainly on model interpretability. Patrick is also currently an adjunct professor in the Department of Decision Sciences at George Washington University, where he teaches graduate classes in data mining and machine learning. Prior to joining H2O.ai, Patrick held global customer facing roles and R & D research roles at SAS Institute. He holds multiple patents in automated market segmentation using clustering and deep neural networks. Patrick was the 11th person worldwide to become a Cloudera certified data scientist. He studied computational chemistry at the University of Illinois before graduating from the Institute for Advanced Analytics at North Carolina State University.

Leave a Reply

Exploring the Next Frontier of Automatic Machine Learning with H2O Driverless AI

At H2O.ai, it is our goal to democratize AI by bridging the gap between the

July 28, 2020 - by Jo-Fai Chow
In a World Where… AI is an Everyday Part of Business

Imagine a dramatically deep voice-over saying “In a world where…” This phrase from old movie

July 22, 2020 - by Ellen Friedman, PhD
Running Sparkling Water in Kubernetes

Sparkling Water can now be executed inside the Kubernetes cluster. Sparkling Water provides a Beta

July 10, 2020 - by Jakub Hava
From GLM to GBM – Part 2

How an Economics Nobel Prize could revolutionize insurance and lending Part 2: The Business Value of

July 9, 2020 - by Patrick Hall and Michael Proksch
A Inteligência Artificial está transformando e alavancando negócios. Entenda como e por quê

Você sabia que inteligência artificial e machine learning não são conceitos novos? Pois eles surgiram

June 26, 2020 - by Daniel Garbuglio
On-Ramp to AI

The path to democratize AI starts with one class Artificial Intelligence (AI) is like a superhighway,

June 11, 2020 - by Rafael Coss

Join the AI Revolution

Subscribe, read the documentation, download or contact us.

Subscribe to the Newsletter

Start Your 21-Day Free Trial Today

Get It Now
Desktop img