Become familiar with different analytical tools, based on data, to make business decisions Capacity to develop skills to analyze and find relationships between many variables/features Relax some of the assumptions in classical linear regression Deal with the curse of dimensionality in high-dimensional problems Acquire knowledge about the main tools in advanced predictive tools and handle the R language with those models

Introduction Feature Engineering: non-linearities and interactions Efficient Estimation in Least-Squares (QR and SVD) Robustness Variable Selection Regularization tools (shrinkage) Dimension-reduction techniques k-NN Decision Trees and Random Forests

Lectures (50% of the sessions): the contents of the course will be introduced, explained and illustrated with examples. Teaching materials will be provided on Aula Global. Computer Labs (50% of the sessions): Examples and cases studies with the R language.