Course title 
Machine Learning and Econometrics 
Semester 
1102 
Designated for 
COLLEGE OF SOCIAL SCIENCES GRADUATE INSTITUTE OF ECONOMICS 
Instructor 
JUICHUNG YANG 
Curriculum Number 
ECON7225 
Curriculum Identity Number 
323EM1790 
Class 

Credits 
3.0 
Full/Half Yr. 
Half 
Required/ Elective 
Elective 
Time 
Thursday 2,3,4(9:10~12:10) 
Remarks 
Restriction: MA students and beyond OR Restriction: Ph. D students The upper limit of the number of students: 20. 


Course introduction video 

Table of Core Capabilities and Curriculum Planning 
Table of Core Capabilities and Curriculum Planning 
Course Syllabus

Please respect the intellectual property rights of others and do not copy any of the course information without permission

Course Description 
This is a course about machine learning and econometrics for graduate students. Machine learning uses data to predict some variable as a function of other variables, and econometrics use statistical methods for prediction, inference, and causal modeling of economic relationships (Varian, 2014). In the past few decades, computerbased technology allows people to collect enormous data sets, orders of magnitude larger than those that classic statistical theory was designed to deal with. Huge data demands new methodology, and the demand is being met by a burst of innovative computerbased statistical algorithms in estimation and prediction. While algorithmic invention is a more freewheeling and adventurous enterprise, inference is playing catchup as it strives to assess the accuracy, good or bad, of some hot new algorithmic methodology. In other words, the inference / algorithm race is a tortoiseandhare affair (Efron and Hastie, 2016). 
Course Objective 
In this course, we as a group of welltrained econometricians are going to learn some machine learning together. On the estimation / prediction side, we will talk about techniques such as Lasso, neural networks, and random forests. On the inference / causal modeling side, we will discuss some ideas about inference after using these machine learning techniques, and inference methods based on / inspired by the computerbased statistical algorithms, such as generalized random forests and double/debiased machine learning. More importantly, we will talked about the inference questions which haven't been answered, and you are more than welcomed to join us and work on these unanswered questions as your research projects. 
Course Requirement 
1. A midterm exam (40%) by April 14.
2. A final presentation (60%) by May 26.
 The final project can be an individual work or a teamwork with <= 2 team members in total.
 It can be a theoretical study, a Monde Carlo experiment or an empirical work.
 You should talk to me about your work by April 21. 
Student Workload (expected study time outside of class per week) 

Office Hours 

Designated reading 
James, Gareth, Daniela Witten, Trevor Hastie, and Robert Tibshirani (2021).
An Introduction to Statistical Learning: With Applications in R, Second Edition. Springer.

References 
Efron, Bradley and Trevor Hastie (2016).
Computer Age Statistical Inference: Algorithms, Evidence and Data Science. Cambridge.

Grading 
