This course introduces the fundamental concepts in data analysis and statistical learning, as well as the basics of predictive modeling.
This course introduces basic and some advanced methods in unsupervised learning (e.g. dimensionality reduction, cluster analysis) and supervised learning (e.g. parametric model, trees and random forests, boosting). Examples of applications in management illustrate the use of these methods.
- Basics of supervised and unsupervised learning.
- Dimensionality reduction techniques (principal components and factor analysis).
- Hierarchical and non-hierarchical cluster analysis.
- Basics of predictive modeling: Sample division cross-validation bootstrap.
- Parametric models for predictive modeling.
- Association rules (market basket analysis).
- Basic recursive partitioning methods: CART random forest variable importance boosting trees.
- Other topics: Support vector machines nearest neighbor methods basic survival analysis missing data.