Presented By O’Reilly and Cloudera
Make Data Work
21–22 May 2018: Training
22–24 May 2018: Tutorials & Conference
London, UK

Executive Briefing: Why machine learned models crash & burn in production and what to do about it

David Talby (Pacific AI)
17:2518:05 Wednesday, 23 May 2018

Who is this presentation for?

Executives, chief architects, product & engineering leaders, building data science based teams & products

Prerequisite knowledge

Basic familiarity with machine learning, at a business/product level, is assumed.

What you'll learn

Understanding of the key risks and best practices to consider when building machine-learning-intensive products and teams.

Description

Much progress has been made over the past decade on process and tooling for managing large-scale, multi-tier, cloud apps and APIs, but there is far less common knowledge on best practices for managing machine-learned models (classifiers, forecasters, etc.), especially beyond the modeling, optimization, and deployment process once these models are in production.

A key mindset shift required to address these issues is understanding that model development is different than software development in fundamental ways. This talk covers these key differences:

  • Concept drift – machine learned models begin degrading as soon as they’re deployed, and must adapt to a changing environment
  • Locality and limited reuse and generalization of models
  • A/B testing challenges, making it very hard in practice to know which model will perform better in production
  • Semi-supervised and adversarial learning scenarios, which require modeling and optimizing models only once they’re in production
  • The impact of all of the above on product planning, staffing, and client expectation management

This talk covers key best practices that executives, solution architects and delivery teams must take into account when committing to successfully deliver and operate data science intensive systems in the real world.

Photo of David Talby

David Talby

Pacific AI

David Talby is a chief technology officer at Pacific AI, helping fast-growing companies apply big data and data science techniques to solve real-world problems in healthcare, life science, and related fields. David has extensive experience in building and operating web-scale data science and business platforms, as well as building world-class, Agile, distributed teams. Previously, he was with Microsoft’s Bing Group, where he led business operations for Bing Shopping in the US and Europe. Earlier, he worked at Amazon both in Seattle and the UK, where he built and ran distributed teams that helped scale Amazon’s financial systems. David holds a PhD in computer science and master’s degrees in both computer science and business administration.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)