Machine Learning in Finance:

• Random matrix theory for big data models with a large number of predictors:

– (Benign) overfitting the data in-sample leads to good performance out-of-sample: When and why?

– Efficient penalization in the Big Data Regime

– The virtue of complexity for return prediction

• The link between big data models, characteristics, and neural networks:

– Deep learning, shallow learning, and their connections. When (and why) do we need deep learning?

– Initializing neural nets, wide nets versus deep nets.

• High dimensional factor models for the cross-section of returns:

– The tension between conditional and unconditional models.

– Complexity for the cross-sectional asset pricing

– Efficient factor portfolios and the pricing kernel in the complex regime

– From ridge penalties to efficient non-parametric shrinkage

• Implementable Efficient Frontier:

– The economics of adjustment costs

– Propagation of shocks

– Hysteresis and (long term) expectations

Empirical Projects in Banking:

Students get a quick overview of causal inference in empirical finance. They learn about a few practical applications (papers). Students then pick a topic / research question (on their own, or picked from a list of suggested topics) and then answer that question using the methods learned in the course. The students can work together in groups of 2 if they prefer. Finally, students prepare a short paper and a presentation of their early findings. The course is optimal for students to explore any early empirical research idea using methods of causal inference (or machine learning).

Machine Learning in Finance:

• Understand and apply modern methods from random matrix theory for big data models with many predictors.

• Understand and apply big data models and neural networks.

• Construct high-dimensional factor models for the cross-section of returns and develop an efficient, theory-based way of optimally incorporating high-dimensional information into portfolio construction.

• Understand the role of trading costs, price impact, and the nature of shock propagation for optimal strategic asset allocation

Empirical Projects in Banking:

Student will learn (repeat) causal inference methods and their application. They will learn how to explore a research question, find data and write a short exploration of the topic. Students will learn how to conduct all early-stage parts of a research project including: literature research, data acquisition, early data analysis (using python, R or stata) and writing of a short paper.

Machine Learning in Finance:

Attendance is required

Empirical Projects in Banking:

The course will have two mandatory lecture sessions, which students are expected to attend. Afterwards students will attend regular individual (or group) meetings to assess the progress of their research project. In the end there will be a final session with presentations (to be scheduled).

Machine Learning in Finance:

Coding (Python) take-home assignment.

Empirical Projects in Banking:

Students write a short paper (no more than 10 pages; 1-2 tables / figures) and prepare a short presentation.

Please log in with your WU account to use all functionalities of read!t. For off-campus access to our licensed electronic resources, remember to activate your VPN connection connection. In case you encounter any technical problems or have questions regarding read!t, please feel free to contact the library at readinglists@wu.ac.at.

Machine Learning in Finance:

Basic probability and linear algebra.

Machine Learning in Finance:

Professor: Semyon Malamud, Email: semyon.malamud@epfl.ch

Empirical Projects in Banking:

Professor: Oliver Rehbein, Email: office-vgsf@wu.ac.at