Machine Learning/Data Science

Catalog description

This course provides an introduction to Machine Learning, Data Science and Predictive Analytics. It includes linear regression, logistic regression, nearest neighbor methods, decision trees, neural networks, deep learning methods, clustering, principal components analysis, and resampling methods such as cross-validation and bootstrapping. If time permits, it will also include support vector machines and machine learning methods for numerical optimization such as genetic and evolutionary algorithms and swarm intelligence algorithms. The Python programming language or the R software will be used to apply statistical and machine learning methods to real data sets. Whenever appropriate, the mathematical background of machine learning methods will be covered. Students will be required to work on a final data analysis project and present their findings in class. This course and DSC 424 (Regression and Time Series) together cover the topics in the SOA (Society of Actuaries) exam in SRM (Statistics for Risk Modeling) and provide an intro to the PA (Predictive Analytics) exam. Also, this course and DSC 424 cover several topics in the CAS (Casualty Actuarial Society) exams in MAS (Modern Actuarial Statistics) I and II.