You are viewing content from a past/completed QCon

Presentation: How to Prevent Catastrophic Failure in Production ML Systems

Track: AI/Machine Learning without a PhD

Location: Mountbatten, 6th flr.

Duration: 10:35am - 11:25am

Day of week: Monday

Slides: Download Slides

Share this on:

This presentation is now available to view on

Watch video with transcript


AI systems can fail catastrophically and without warning, a characteristic not welcomed in the corporate environment. Martin will describe the unpredictable nature of artificial intelligence systems and how mastering a handful of engineering principles can mitigate the risk of failure. You’ll learn the kinds of errors artificial intelligence systems make, how to build systems that protect against common errors, and why evaluation can be much harder than it seems.

Speaker: Martin Goodson

Chief Scientist/CEO @EvolutionAI

Martin Goodson is the chief scientist and CEO of Evolution AI, which develops a platform for large-scale natural language processing. Martin has designed machine learning products that are in use at FTSE 100 and Fortune 500 companies like Dun & Bradstreet, Time Inc., Royal Bank of Scotland, and Condé Nast. Previously, Martin performed machine learning research at the University of Oxford. He runs the largest community of machine learning practitioners in Europe, Machine Learning London, and convenes the Royal Statistical Society roundtable, AI in Financial Services. Martin’s work has been covered by publications such as the Economist, Quartz, Business Insider, TechCrunch, and others.

Find Martin's blog on data science here:

Find Martin Goodson at

Last Year's Tracks