Instructor: Thierry Denoeux

Description: This course is an introduction to statistical learning, with examples of application to econometrics.

Program

1. Introduction to machine learning
2. Linear classification
3. Model selection
4. Splines and generalized additive models
5. Tree-based and ensemble methods
6. Kernel-based classification and regression
7. Neural networks

Recommended reading:

• An Introduction to Statistical Learning with Applications in R
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction
• Pattern Recognition and Machine Learning

Slides

1. Introduction
2. Linear and Quadratic Classification
3. Model Selection
4. Splines and Generalized Additive Models
5. Tree-based and ensemble methods
6. Kernel-based classification and regression
7. Neural networks and deep learning

Recordings

1. Lecture 1 (April 4, 2023)
2. Lecture 2 (April 7, 2023)
3. Lecture 3 (April 11, 2023)
4. Lecture 4 (April 12, 2023)
5. Lecture 5 (April 18, 2023)
6. Lecture 6 (April 19, 2023)
7. Lecture 7 (April 29, 2023)
8. Lecture 8 (May 3, 2023)
9. Lecture 9 (May 5, 2023)
10. Lecture 10 (May 11, 2023)
11. Lecture 11 (May 13, 2023)
12. Lecture 12 (May 19, 2023)
13. Lecture 13 (May 23, 2023)
14. Lecture 14 (May 24, 2023)

Exercises

1. K-NN regression and bias-variance decomposition
   • Solutions
2. Linear and Quadratic Classification
   • Solutions
3. Model selection
   • Solutions
4. Splines and Generalized Additive Models
   • Solutions
5. Tree-based and ensemble methods
   • Solutions
6. Kernel-based classification and regression
   • Solutions
7. Neural networks and deep learning
   • Solutions

Datasets

• Default credit card
• Movie buzz
• Expenditure and Default Data
• Countries
• Program effectiveness
• CP time series
• German health care
• Communities and crime