Applied Machine Learning in Economics and Finance (Seminar)

Modern empirical research in economics and finance uses computer intensive methods for the analysis of complex data sets. The estimates are based on algorithmic methods to cope with a whopping number of covariates and possible model specifications. The problem is prevalent e.g., in macroeconomic forecasting, in asset pricing and portfolio selection, and in the evaluation of causal treatment effects of public policies. Consequently, empirical studies in economics and finance rely more and more on machine learning techniques (e.g., lassoing, support vector machines, artificial neuronal nets).

The goal of this seminar is to acquaint students with the necessary toolbox of machine learning techniques. Students must write an empirical research paper in which a novel and/or advanced ML method is applied to shed more light on a real-world problem.

Time and Date

The seminar will take place as a block seminar on the following two days:

  • April 5-6, 2022, 08:15 – 18:00 in room D406


Econometrics I and Advanced Econometrics (or equivalent). Participation in the courses Financial Econometrics and/or Topics in Advanced Econometrics is an advantage but not a prerequisite. We expect that students have a decent programming background in either MatLab, R or Python or at least willing to invest sufficient effort to learn one of these languages.

Organizational Issues

• For enrollment via registration is possible from June 29 to July 5, 2021

• For more information contact Winfried Pohlmeier, F319, Tel. 2660,

• Kick-off Meeting October 25, 2021 17:00 - 18:30 in room H308.

• Seminar participants must decide on the topics until Nov. 02, 2021.

• Submission deadline of the seminar paper: March 31st, 2022.

• Joint work is possible. 

•  ECTS: 6 credits.

Suggested Topics

  1. Asset Pricing and Machine Learning: How good are Neuronal Nets?
  2. Estimating Nonlinear Factor Models by Artificial Neuronal Nets? Theory and Application
  3. Bagging Portfolios: Do we gain anything from that?
  4. Learning from Machines about Financial Risks: Bagging the Value-at Risk and Expected Shortfall
  5. Measuring peer effects in education using network information
  6. Team Captain or Cheer Leader: Who is central in School Classes?
  7. How to cope with isolated individuals in networks? An Empirical Study using School Data.
  8. Are women the better peers? Accounting for Gender Heterogeneity in Networks
  9. Elicitability: What is a good loss function?
  10. Significance Testing in the Presence of Heterogeneity, Serial Correlation and Outliers: Theory and an Application of the Ibragimov–Müller t-values
  11. Which model to select? All of them! Frequentist model averaging methods for parametric models with Application to Something.
  12. Sentiment and Financial Risks using Natural Language Processing and Quantile Regressions

This list is incomplete. The topics above are only first suggestions and are supposed to give a flavor of the seminar’s content. We will assign the final topics according to the student’s background and interests.