Achieving Salesforce-scale machine learning in production

This will be presented in English.

Sarah Aerni (Salesforce Einstein)
11:1511:55 Friday, June 21, 2019

您将学到什么 (What you'll learn)

  • Learn how to set up your organization for data science success
  • Gain foundational elements required to achieve data science in production

描述 (Description)

In the fourth industrial revolution, every organization must successfully leverage its data to better serve its customers and more effectively run its business. And while machine learning and artificial intelligence were historically viewed as a competitive advantage, they will become an essential part of every business process. They may well become necessary. However, the journey to bringing these techniques to production is challenging. Hurdles exist in technical implementation and talent acquisition.

Sarah Aerni examines the lessons learned in business, technology, and the process undertaken by Salesforce Einstein, an agile partner to over 100,000 customers. How does Salesforce achieve this scale? Hear about use cases, oft-missed foundational elements for deployment, and the evaluations that must happen along the way and learn to achieve and sustain models in production—and where to go from there. Sarah shares the company’s perspectives on how to measure and achieve success for data science in production. The foundational elements of any platform are the ability for data scientists to experiment and rapidly deploy to production. With the open source autoML library (TransmogrifAI), it’s easy for data scientists to contribute new ways of solving challenging problems and evaluating them at scale using experimentation frameworks. The platform helps you ship the code to production to all customers simultaneously, automating the process of retraining thousands of models and shipping billions of predictions per day.

With modeling of course comes the need to detect issues and identify opportunities for improvements. Sarah walks you through how the company uses alerting and monitoring to keep track of the individual models that 100,000+ customers can build in a completely automated way and drive the data science backlog. She shares lessons learned around rapid iteration and how to ensure data science innovation continues in a truly agile methodology.

Photo of Sarah Aerni

Sarah Aerni

Salesforce Einstein

Sarah Aerni is a director of data science at Salesforce Einstein, where she leads teams building AI-powered applications using autoML. Previously, she led teams in healthcare and life sciences at Pivotal, building models for customers, and she cofounded a company offering expert services in informatics to both academia and industry. Sarah holds a PhD in biomedical informatics from Stanford University, where she performed research at the interface of biomedicine and machine learning.

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)