This course is available with permission as an outside option to students on other programmes where regulations permit. This course uses controlled access as part of the course selection process. For information on controlled access courses, including eligibility, application processes, deadlines, and departmental contact details, please refer to the Controlled Access Courses webpage.

New course for 2027/28 academic session

Any external student must have successfully completed EC400 or EC451 in September and EC4C1 or EC4C2, or Equivalent.

Deadline for application: Please apply as soon as possible after the opening of course selection for all courses.

For queries, contact: Econ.msc@lse.ac.uk

Pre-requisites:

Before taking this course, students must have completed: (EC451 or EC400) and (EC4C2 or EC4C1).

Additional requisites:

Students will benefit from a familiarity with programming Python, though this is not essential as students will have access to dedicated workshops and drop-in support sessions, as well as access to and the Department of Economics Python for Economics Moodle page, designed in collaboration with the Digital Skills Lab for supporting Economics courses that make use of Python.

This course explores advanced econometric methods with a focus on AI and machine learning-based methods and their applications to large datasets using Python programming.  Topics include supervised learning (regression, classification, trees/random forests, and artificial neural networks/deep learning), unsupervised learning (cluster analysis, principal component analysis, matrix completion), generative AI (text data analysis in economics), and recent developments (double machine learning and generative adversarial networks).

Every topic is motivated and illustrated by real economic examples based on recent research articles in economics (including housing price prediction, classification of text data, evaluation of summer job program, measurement of CEO behaviour, grouped fixed effect, macroeconomic forecasting, panel data completion, text analysis in economics).

20 hours of lectures and 9 hours of seminars in the Winter Term.
1 hour of seminars in the Spring Term.

This course has a reading week in Week 6 of Winter Term.

Two pieces of formative work will be assessed and written feedback provided. 

• Athey, S. and G. W. Imbens (2019) Machine learning methods that economists should know about, Annual Review of Economics, 11, 685-725.
• Mullainathan, S. and J. Spiess (2017) Machine learning: an applied econometric approach, Journal of Economic Perspectives, 31, 87-106.
• Korinek, A. (2023) Generative AI for economic research: use cases and implications for economists, 61, 1281-1317.
• Ash, E. and S. Hansen (2023) Text algorithms in economics, 15, 659-688.
• Dell, M. (2025) Deep learning for economists, Journal of Economic Literature, 63, 5-58.
• Hastie, T., Tibshirani, R. and J. Friedman (2009) The Elements of Statistical Learning, Springer.
• James, G., Witten, D., Hastie, T., Tibshirani, R. and J. Taylor (2013) An Introduction to Statistical Learning: with Applications in Python, Springer.
• Chernozhukov, et al (2024) Applied Causal Inference Powered by ML and AI (used for topics on causal inference).
• Taddy, M. (2023) Business Data Science: Combining Machine Learning and Economics to Optimise, Automate, and Accelerate Business Decisions, McGraw Hill.
• Zollanvari, A. (2023) Machine Learning with Python: Theory and Implementation, Springer.
• Hull, I. (2021). Machine learning for economics and finance in TensorFlow 2. Apress: Berkeley, CA, USA.

For each topic, students will discuss economics applications drawn from recent economics research. A full reading list will be provided on Moodle.

Exam (75%), duration: 120 minutes, reading time: 15 minutes in the Spring exam period.

Continuous assessment (25%).