Month: September 2016

Title:  Electoral College Math:  How to Become President with 20% of the Popular Vote

Abstract: The Electoral College makes it possible to become U. S. President with less than a majority of the popular vote. In a two-candidate election, what is the minimal percentage of the popular vote possible for a winning candidate? In this talk we’ll first mimic an approach suggested by George Pólya that to find a theoretical solution. We’ll then make use of of tools not readily available to Pólya – spreadsheets and binary linear integer problem software — to see if we can improve on his results using actual presidential election data. Anyone with a vague recollection of high school algebra has the mathematical background necessary to enjoy this talk.

Title:  Sequential data mining

Abstract:  Data representing DNA, proteins, literature, weather, and the stock market all share one common characteristic: their data are sequential. Sequence data present some of the most challenging problems for machine learning and data mining methods. In this talk, Professor Brian King will present a generalized, probabilistic framework for modeling sequential data. He will show how he and his students have adapted this model for classification and prediction tasks, reporting results from recent studies.