Recommendation engines: A key personalization feature of modern web applications

Thu, Jun 11 6:00pm

Presentation Overview:

In today's world, we're overwhelmed with choices; a plethora of options are available for nearly every aspect of our lives. We need to make choices on a daily basis: from automobiles to home theatre systems; from finding Mr. or Ms. "Perfect" to selecting attorneys or accountants; from books and newspapers to wikis and blogs; from movies to songs, and so on.

Can we provide the users of our applications with suggestions about all these choices that they have to make? The brief answer is a resounding yes! The key element that provides suggestions, in any application, is generically called a recommendation engine.

The talk will cover both collaborative filtering and content-based recommendation engines. I will explain what they are and how to use them. The talk will begin by describing the problem of recommending songs in an online music store. Once we cover all the basic concepts in our online music store, we'll make things a lot more interesting by presenting more complicated cases.

Presenter Bio:

Babis Marmanis is a pioneer in the adoption of machine learning techniques for industrial solutions, and also a world expert in supply management. He has about twenty years of experience in developing professional software. Currently, he is the director of R&D and chief architect, for expense management solutions, at Emptoris, Inc. Babis is a senior member of ACM and holds a Ph.D. in applied mathematics and scientific computing from Brown University.