← jasminehao.com
ECON6083 · M5 2026

Machine Learning in Economics

Prof. Jasmine Hao Mar 18 – May 4, 2026 10 Lectures · 3 hrs each 5 Weeks
Lectures
Slides and in-class exercises are released the day before each lecture. Locked items will unlock automatically.
Slides are provided as PDF files. Click to download or view in your browser.
Past Slides — Spring 2023
Lecture slides from the 2023 offering of ECON 6083.
Slides are provided as PDF files. Click to download or view in your browser.
Lecture 0

Introduction

Download PDF →
Lecture 1.1

Lasso

Download PDF →
Lecture 1.2

Belloni et al. (2014, JEP)

Download PDF →
Lecture 1.3

Hansen & Kozbur — Lasso IV

Download PDF →
Lecture 1.4

Lasso Application

Download PDF →
Lecture 2.1

Tree-Based Methods

Download PDF →
Lecture 2.2

Heterogeneous Treatment Tree

Download PDF →
Lecture 2.3

Narayanan & Kalyanam (2020)

Download PDF →
Lecture 3.0

Forest for Inference

Download PDF →
Lecture 3.1

Wager & Athey (2018)

Download PDF →
Lecture 3.2

Athey, Tibshirani & Wager (2019)

Download PDF →
Lecture 4.1

Gentzkow, Taddy & Kelly (JEP)

Download PDF →
Lecture 4.2

Grimmer & Stewart (2013)

Download PDF →
Lecture 5.1

Finite Mixture

Download PDF →
Lecture 5.2

Clustering

Download PDF →
Course Schedule
Choose your section to view the exact dates and locations. All sections cover the same material.
10
Lectures
5
Weeks
40%
Final Project
Class A (Tue & Fri AM)
Class B (Tue & Fri PM)
Class A
Schedule: Tuesday & Friday | Time: 9:30 AM - 12:30 PM
Venue: Cyberport 4 - Classroom J
Exceptions: Mar 24 & Mar 27 → Cyberport Classroom EFG
⚠️ Important Note for March 24: Class A and Class B will be in different classrooms on March 24.
• Class A (AM): Cyberport Classroom EFG
• Class B (PM): Cyberport Classroom H
Date Day Topic Location
Mar 20
2026		 Fri L1Introduction & Supervised Learning Cyberport 4 - Classroom J
Mar 24
2026		 Tue L2Regularization & High-Dim Regression Cyberport Classroom EFG
Mar 27
2026		 Fri L3Trees, Random Forests & Boosting Cyberport Classroom EFG
Mar 31
2026		 Tue L4Cross-Validation & Model Selection Cyberport 4 - Classroom J
Apr 10
2026		 Fri L5Double/Debiased Machine Learning Cyberport 4 - Classroom J
Apr 14
2026		 Tue L6Heterogeneous Treatment Effects Cyberport 4 - Classroom J
Apr 17
2026		 Fri L7DAGs & Structural Causal Models Cyberport 4 - Classroom J
Apr 21
2026		 Tue L8Instrumental Variables & DML-IV Cyberport 4 - Classroom J
Apr 24
2026		 Fri L9Difference-in-Differences & RDD Cyberport 4 - Classroom J
Apr 28
2026		 Tue L10Optimal Policy Learning & Text as Data Cyberport 4 - Classroom J
Apr 30 – May 4 — Study Period & Final Project Completion
Class B
Schedule: Tuesday & Friday | Time: 2:00 PM - 5:00 PM
Venue: Cyberport 4 - Classroom J
Exceptions: Mar 24 → Cyberport Classroom H; Mar 27 → Cyberport Classroom EFG
⚠️ Important Note for March 24: Class A and Class B will be in different classrooms on March 24.
• Class A (AM): Cyberport Classroom EFG
• Class B (PM): Cyberport Classroom H
Date Day Topic Location
Mar 20
2026		 Fri L1Introduction & Supervised Learning Cyberport 4 - Classroom J
Mar 24
2026		 Tue L2Regularization & High-Dim Regression Cyberport Classroom H
Mar 27
2026		 Fri L3Trees, Random Forests & Boosting Cyberport Classroom EFG
Mar 31
2026		 Tue L4Cross-Validation & Model Selection Cyberport 4 - Classroom J
Apr 10
2026		 Fri L5Double/Debiased Machine Learning Cyberport 4 - Classroom J
Apr 14
2026		 Tue L6Heterogeneous Treatment Effects Cyberport 4 - Classroom J
Apr 17
2026		 Fri L7DAGs & Structural Causal Models Cyberport 4 - Classroom J
Apr 21
2026		 Tue L8Instrumental Variables & DML-IV Cyberport 4 - Classroom J
Apr 24
2026		 Fri L9Difference-in-Differences & RDD Cyberport 4 - Classroom J
Apr 28
2026		 Tue L10Optimal Policy Learning & Text as Data Cyberport 4 - Classroom J
Apr 30 – May 4 — Study Period & Final Project Completion
Date Week Topic Location
Mar 20 (Thu)
9:00 AM - 12:00 PM		 Week 1 L1Introduction & Supervised Learning TBD
Mar 24 (Mon)
9:00 AM - 12:00 PM		 Week 1 L2Regularization & High-Dim Regression TBD
Mar 31 (Mon)
9:00 AM - 12:00 PM		 Week 2 L3Trees, Random Forests & Boosting TBD
Apr 3 (Thu)
9:00 AM - 12:00 PM		 Week 2 L4Cross-Validation & Model Selection TBD
Apr 7 (Mon)
9:00 AM - 12:00 PM		 Week 3 L5Double/Debiased Machine Learning TBD
Apr 10 (Thu)
9:00 AM - 12:00 PM		 Week 3 L6Heterogeneous Treatment Effects TBD
Apr 14 (Mon)
9:00 AM - 12:00 PM		 Week 4 L7DAGs & Structural Causal Models TBD
Apr 17 (Thu)
9:00 AM - 12:00 PM		 Week 4 L8Instrumental Variables & DML-IV TBD
Apr 21 (Tue)
9:00 AM - 12:00 PM		 Week 5 L9Difference-in-Differences & RDD TBD
Apr 24 (Fri)
9:00 AM - 12:00 PM		 Week 5 L10Optimal Policy Learning & Text as Data TBD
Apr 30 – May 4 Exam Week Study Period & Final Project Completion
📍 Location Information Classroom locations will be announced via email and posted here before the first lecture. Please check your university email for updates.
Final Project
Choose Track 1 (empirical replication & extension) or Track 2 (literature review). Both require a 12–15 page LaTeX report.
The final project is assigned from Week 1 and due one week after the last lecture. Work individually or in groups of two.
Track 1

Empirical Replication & Extension

Replicate a landmark causal ML paper using original (or similar) data, then propose and implement a meaningful extension.

  • 6 curated paper options (DML, Causal Forests, DiD, SCM, Policy Learning, Text as Data)
  • Starter code and data links provided
  • Graded on replication accuracy (40%), extension originality (30%), writing (20%), and code quality (10%)
View Full Guide → LaTeX Template
Track 2

Literature Review

Conduct a structured literature review on a specific ML-in-economics domain. Compare prediction-focused and causal-inference strands.

  • Snowball search: backward (bibliography) + forward (Google Scholar “Cited by”)
  • Synthesize 10–15 core papers thematically
  • Graded on literature coverage (35%), analysis & synthesis (35%), writing (20%), and original insight (10%)
View Full Guide →

Submit a .zip file containing: (1) code/ — clean, reproducible Python scripts, (2) report.pdf — 12-15 page academic paper (LaTeX template provided).

Due: One week after last lecture
Weight: 40% of course grade
Team: Individual or pairs