Automated Decision Making Online

Data Science
Location: King's Suite - Balmoral Level: Intermediate
Average rating: ***..
(3.83, 6 ratings)
Slides:   1-PDF 

Analytics that doesn’t lead to action is wasted effort. Taking action often means human involvement, which has several drawbacks: it creates a slow feedback cycle, people are notoriously bad at balancing risk and reward, and they’re expensive. Getting the computer to do this job is an attractive alternative, but how exactly can we do this? In this talk I will discuss a class of algorithms, known as bandit algorithms, that address a simple but common decision making problem. The talk will be eminently practical, focusing on the main concepts behind the algorithms and issues that arise in practice.

  • Why automated decision making
  • The bandit problem and applications
  • Exploration and exploitation
  • e-Greedy
  • Probability matching
  • Adding context
  • Real world issues
  • Further Reading
Photo of Noel Welsh

Noel Welsh

Underscore Consulting

Noel has over fifteen years experience in software architecture and development, and over a decade in machine learning and data mining. His current project is Myna, which makes bandit algorithms accessible to all. Previous projects he’s been involved with include one of the first commercial products to apply machine learning to the Internet (eventually acquired by Omniture), a BAFTA award winning website, and a custom CMS used daily by thousands of students.

Noel is an active writer, presenter, and open source contributor. Noel has a PhD in machine learning from the University of Birmingham.

Sponsors

Sponsorship Opportunities

For exhibition and sponsorship opportunities, contact Susan Stewart at sstewart@oreilly.com

Media Partner Opportunities

For information on trade opportunities with O'Reilly conferences email mediapartners
@oreilly.com

Press & Media

For media-related inquiries, contact Maureen Jennings at maureen@oreilly.com

Contact Us

View a complete list of Strata contacts