This week, we’ll be featuring a series of shows recorded from Strange Loop, a great developer-focused conference that takes place every year right in my backyard! The conference is a multi-disciplinary melting pot of developers and thinkers across a variety of fields, and we’re happy to be able to bring a bit of it to those of you who couldn’t make it in person! In this episode, I speak with Sam Ritchie, a software engineer at Stripe. I caught up with Sam RIGHT after his talk at the conference, where he covered his team’s work on explaining black box predictions.
Subscribe: iTunes / SoundCloud / Google Play / Stitcher / RSS
In our conversation, we discuss how Stripe uses black box predictions for fraud detection, and he gives a few use case scenarios. We discuss Stripe’s approach for explaining those predictions as well as other approaches, and briefly mention Carlos Guestrin’s work on LIME paper, which he and I discuss in TWiML Talk #7.
Thanks to our Sponsor
We’d like to send a big shoutout to Nexosis, who helped make this series possible. Nexosis is a company of developers focused on providing easy access to machine learning. The Nexosis Machine Learning API meets developers where they’re at, regardless of their mastery of data science, so they can start coding up predictive applications today, in their preferred programming language. It’s as simple as loading your data and selecting the type of problem you want to solve. Their automated platform trains and selects the best model fit for your data and then outputs predictions. Be sure to also get your free Nexosis API key and discover how to start leveraging machine learning in your next project at nexosis.com/twiml.
TWiML Online Meetup
The details of our next TWiML Online Meetup have been posted! On Wednesday, December 13th, at 3pm Pacific Time, we will be joined by Bruno Gonçalves, who will be presenting the paper “Understanding Deep Learning Requires Rethinking Generalization”. If you’re already registered for the meetup, you should have already received an invitation with all the details. If you still need to register for the meetup, head over to twimlai.com/meetup to do so. We hope to see you there!
Mentioned in the Interview
- Sam Presentation from Strange Loop 2017
- Slides from Sam’s Presentation
- Get your free Nexosis API key here!
- “Mythos of Model Interpretability” by Zachary Lipton”
- Carlos Guestrin – LIME
- DARPA: Explainable AI
- DARPA: Explainable AI Slideshow
- Stuart Russell’s Program on Human Compatible AI
- Interpretable ML Symposium
- AI transparency from the “robotics and artificial intelligence” report from the UK parliament, related to the GDPR
- TWiML Online Meetup – Kevin Tee – Active Preference Learning for Personalized Portfolio Construction
- Strange Loop 2017 Series
- TWiML Events Page
- TWiML Meetup
- TWiML Newsletter