Introduction to Statistical Learning

The course provides a first insight into statistical learning, which refers to a set of tools for modeling and understanding complex datasets. It is a recently developed area in statistics and blends with parallel developments in computer science and, in particular, machine learning. With the explosion of “Big Data” problems, statistical learning has become a very hot field in many scientific areas as well as marketing, finance and other business disciplines. Besides an introduction to the characteristics, benefits and challenges of Big Data, four applications from the field of statistics are presented.

This course can might be seen as a complement to traditional statistical courses. It will give a introduction into the following topics:

• Introduction
• What is Big Data?
• Main Sources
• Benefits and Challenges

• Big Data Sets
• Analyzing Big Datasets
• Big Data Analysis in this Workshop

• Visualization

• Classification
• Model training
• Decision Trees
• Bagged Trees and Random Forests
• Boosted Trees
• Penalized Regression
• Linear Regression (reminder)
• Penalized Regression (Lasso, Ridge, Elastic Net)

• Clustering
• k-Means
• SOM

Requirements

This course addresses all who want to enlarge their knowledge of traditional statistics. Thus, a basic knowledge of statistics (at least up to linear regression) is mandatory. Please note that this course has a statistical focus, therefore technical issues like memory allocations and data storage are not included.

Participants should possess knowledge of basic statistical methods, such as hypothesis testing and linear regression.