Fundamentals of Data Science in Engineering Management

Catalog description

In this course, students will learn the fundamentals of data science, including core technical vocabulary and mathematical concepts. This will include topics such as (i) probability through Bayesian techniques; (ii) binary classification; (iii) linear regression for forecasting; (iv) Information measures used in data science, including mutual information, relative entropy (KL divergence), and log loss (cross entropy), (v) Experimental design; and (vi) the roles of training and test data, using Hoeffding's inequality to forecast error rates. Students will apply the above concepts to real-world data, while developing their own models for probabilistic forecasting.