Daniela Witten

Statistical Machine Learning for Real World Problems

What do Netflix, Facebook, cancer researchers, the financial industry, and sociologists have in common? They are faced with vast amounts of data that must be processed in a meaningful way in order to yield useful information. Statistical machine learning is a field at the interface of math, statistics, and computer science that provides tools that can be used to make sense of very large data sets.

In particular, I'll talk about the Netflix problem. How can we use a data set consisting of the ratings given by a huge number of movie viewers to a huge number of movies in order to predict the rating that a new user will give to a new movie?