Course Detail (Course Description By Faculty)

Machine Learning in Finance (35137)

Machine Learning in Finance focuses on the use of machine learning and AI methods and their applications in finance with a particular focus on problems in asset pricing.  This course aims to provide students with the knowledge necessary to best use recent machine learning methods but also to understand their limitations.  We will cover such topics as penalized estimation and its use in forecasting, clustering, factor models and unsupervised learning, neural networks and non-linear prediction, text data and large language models.

It is expected that students will have some exposure to programming in Python.  Students will work with real financial datasets to help gain a better understanding of the methods covered.

Business 41000 (or 41100 or 41210) is a prerequisite. Students must be comfortable with statistics, regression analysis, linear algebra, and Python programming.

There is no required textbook.  Several supplementary texts will be recommended and recent academic papers will be provided on Canvas.

Based on several homework problem sets, a final project, quizzes, and class participation.

  • Allow Provisional Grades (For joint degree and non-Booth students only)
  • Early Final Grades (For joint degree and non-Booth students only)
Description and/or course criteria last updated: June 17 2025
SCHEDULE
  • Winter 2026
    Section: 35137-01
    M 1:30 PM-4:30 PM
    Gleacher Center
    208
    In-Person Only
  • Winter 2026
    Section: 35137-81
    M 6:00 PM-9:00 PM
    Gleacher Center
    208
    In-Person Only

Machine Learning in Finance (35137) - Bybee, Leland>>

Machine Learning in Finance focuses on the use of machine learning and AI methods and their applications in finance with a particular focus on problems in asset pricing.  This course aims to provide students with the knowledge necessary to best use recent machine learning methods but also to understand their limitations.  We will cover such topics as penalized estimation and its use in forecasting, clustering, factor models and unsupervised learning, neural networks and non-linear prediction, text data and large language models.

It is expected that students will have some exposure to programming in Python.  Students will work with real financial datasets to help gain a better understanding of the methods covered.

Business 41000 (or 41100 or 41210) is a prerequisite. Students must be comfortable with statistics, regression analysis, linear algebra, and Python programming.

There is no required textbook.  Several supplementary texts will be recommended and recent academic papers will be provided on Canvas.

Based on several homework problem sets, a final project, quizzes, and class participation.

  • Allow Provisional Grades (For joint degree and non-Booth students only)
  • Early Final Grades (For joint degree and non-Booth students only)
Description and/or course criteria last updated: June 17 2025
SCHEDULE
  • Winter 2026
    Section: 35137-01
    M 1:30 PM-4:30 PM
    Gleacher Center
    208
    In-Person Only
  • Winter 2026
    Section: 35137-81
    M 6:00 PM-9:00 PM
    Gleacher Center
    208
    In-Person Only