Presented By O’Reilly and Intel AI
Put AI to Work
April 29-30, 2018: Training
April 30-May 2, 2018: Tutorials & Conference
New York, NY

Explaining machine learning for consumer loans

4:50pm–5:30pm Tuesday, May 1, 2018
Average rating: ****.
(4.00, 2 ratings)

Who is this presentation for?

  • Business experts, analysts, and machine learning engineers

Prerequisite knowledge

  • Experience explaining models internally or to meet regulatory requirements (useful but not required)

What you'll learn

  • Understand how it's possible to use powerful machine learning models even in regulated industries
  • Explore existing techniques for explaining machine learning models and the decisions they make and learn how to best use them


Historically, the consumer loan industry has restricted itself to using relatively simple machine learning models and techniques to accept or deny loan applicants, because they are easy to understand, easy to explain, and familiar to regulators. However, more powerful (but also more complicated) methods can significantly improve business outcomes.

Sean Kamkar outlines a framework for evaluating, explaining, and managing these more complex methods. Along the way, Sean explores the need within and barriers surrounding the credit underwriting space and offers definitions for concepts around explainability.

Sean Kamkar

Comments on this page are now closed.


05/04/2018 6:39am EDT

Hi, @Sean,
Will the slides be made available? Great talk! Thank you!