Skip to content

ml4econ/lecture-notes-2025

Repository files navigation

Machine Learning for Economists (57750)

Spring 2025 | Hebrew University of Jerusalem

Instructor: Itamar Caspi
Teaching Assistant: Inbar Avni

📅 Spring Semester, 2025
🕒 16:30 - 19:15
🏢 Social Sciences Building, Room 22205
📝 Course Materials
💬 Discussion Forum


Overview

This course integrates data science, machine learning, and econometrics to equip students with fundamental machine learning concepts that can enhance empirical economics research. Students will explore both supervised and unsupervised machine learning methods, with emphasis on their applications in empirical economics. The course highlights the relevance of machine learning to policy analysis and causal inference through real-world applications, empirical research papers, and hands-on assignments.

Learning Objectives

By the end of this course, students will be able to:

  1. Implement data science best practices within empirical economics research
  2. Navigate the challenges and opportunities of working with high-dimensional data in economics
  3. Integrate machine learning techniques into applied economic research

Prerequisites

Students are expected to:

  1. Have their own computers with R, RStudio (Posit), Git, and GitHub Desktop installed
  2. Create free accounts on GitHub and Kaggle

Course Schedule

Note: This schedule may be adjusted based on class interests and time constraints. Please check the course page regularly for updates.

Week Topic
1 Course Overview
2 Basic ML Concepts
3 Reproducibility & ML Workflow
4 Regression and Regularization
5 Classification
6 Trees and Forests
7 Causal Inference
8 High-Dimensional Confounding Adjustment
9 High-Dimensional Heterogeneous Treatment Effects
10 Text as Data
11 Deep Learning
12 Large Language Models

Course Materials

Part I: Machine Learning

  1. Course Overview
    In this lecture, we will introduce the course, its objectives, and the tools we will use.
    HTML | PDF

  2. Basic Machine Learning Concepts
    In this lecture, we will cover the basic concepts of machine learning, including supervised and unsupervised learning, model evaluation, and cross-validation.
    HTML | PDF

  3. ML Workflow
    In this lecture, we will discuss the machine learning workflow, including data preprocessing, feature engineering, and model selection.
    HTML | PDF

  4. Reproducibility
    In this lecture, we will discuss the importance of reproducibility in machine learning and how to achieve it using version control and containerization.
    HTML | PDF

  5. Regression and Regularization
    In this lecture, we will cover regression techniques and regularization methods such as Lasso and Ridge regression, PCR and PLS.
    HTML | PDF
    5.1 Prepare browser data
    5.2 Ridge and lasso simulation
    5.3 Ridge, lasso, PCR and PLS: A Tidymodels Workflow
    5.4 Shrinkage and seection intuition 5.5 Tidymodels Workflow

  6. Classification In this lecture, we will cover classification techniques such as logistic regression.
    HTML | PDF
    6.1 Tidymodels Workflow

  7. Decision Trees and Random Forests In this lecture, we will cover decision trees and random forests, including their advantages and disadvantages.
    HTML | PDF

Part II: Causal Inference and ML

  1. Causal Inference In this lecture, we will review the principles of causal inference, including the potential outcome and DAGs framework HTML | PDF

  2. High-Dimensional Confounding Adjustment In this lecture, we will explore methods for adjusting for high-dimensional confounding in causal inference, including propensity score matching and inverse probability weighting. HTML | PDF

  3. High-Dimensional Heterogeneous Treatment Effects In this lecture, we will discuss methods for estimating heterogeneous treatment effects in high-dimensional settings, including causal trees and forests. HTML | PDF

Part III: Unsupervised Learning and Language Models

  1. Text as Data In this lecture, we will explore how to use text data in machine learning, including text preprocessing, feature extraction, and topic analysis. HTML | PDF

Part IV: Prediction Policy Problems

  1. Prediction Policy Problems In this lecture, we will discuss the challenges of prediction policy problems and algorithmic fairness. HTML | PDF

Projects

  • Kaggle Competition HTML | PDF

  • Replication Assignment

Reading Materials

A comprehensive reading list can be found here.

About the Instructor

Itamar Caspi heads the Monetary Analysis Unit at the Bank of Israel and is an adjunct lecturer at Hebrew University. His research focuses on macroeconomics, monetary economics, and applied econometrics. After starting at the Ministry of Finance in 2010, he joined the Bank of Israel in 2012, later serving as a Research Fellow at the Bank for International Settlements. He holds degrees from Ben-Gurion University (BA), Hebrew University/Tel-Aviv University (MA), Harvard Kennedy School (MPA), and Bar-Ilan University (PhD).


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

About

Machine Learning for Economists (ML4Econ) @ HUJI 2025

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages