Nov 16, Norm Matloff
Student Seminar Series
DATE: Wednesday November 16th, 2016, 12:00pm
LOCATION: MSB 1147 (Colloquium Room).
SPEAKERS: Professor Norm Matloff, Dept Statistics UC Davis
TITLE: “Statistical Issues in Recommender Systems”
ABSTRACT: The term "recommender systems" refers to use of data to predict how well a certain user will like a certain product, with various other applications as well (e.g. how well will a given patient react to a given medicine). The methods used are inherently statistical, notably in the use of latent-variable models and dimension-reduction methods.
This talk will first give an overview of the methodology, and then propose a new approach to the problem. If time permits, some methods for dealing with the huge computational needs of recommender systems will also be discussed.
This seminar series is organized by PhD Students Irene Kim and Clark Fitzgerald.