Big Data Asset Pricing
Overview and Lecture Notes (click links)
Quickly getting to the research frontier
Twenty-first-century topics
Exercises
Beta-dollar neutral portfolios
Construct value factors
Factor replication analysis
High-dimensional return prediction
Research proposal
Details: A Concentrated Class, Partly Hybrid
CBS website: https://phdsupport.nemtilmeld.dk/
Instructors: Lasse Heje Pedersen (LHP) and Theis Ingerslev Jensen (TIJ)
Prerequisites: The course is designed as a first- or second-year Ph.D. course. The prerequisites are knowledge of asset pricing theory and econometrics at a M.Sc. level and an ability to work independently with data using a programmatic computer language such as Matlab, R, or Python. Students must participate in the whole course and do all problem sets.
Aim: The class aims to introduce Ph.D. students in finance and related fields to research methods in big data asset pricing.
Format: The course is partly hybrid and partly in-class, over about 6-8 weeks. There is one lecture per week, except that lectures 5-6 are held on two consecutive days, where participants from abroad must show up physically at Copenhagen Business School.
Time. The class is held in the Spring semester at Copenhagen Business School, likely around February/March.
Lecture plan (preliminary, 3h means 3 hours):
Lecture 1: A primer on asset pricing (3h, hybrid)
Lecture 2: A primer on empirical asset pricing; discussion of Exercise 1 (3h, hybrid)
Lecture 3: Working with big asset pricing data (3h, online)
Lecture 4: The factor zoo and replication crisis; discussion of Exercise 2 (3h, hybrid)
Lecture 5: Machine learning in asset pricing; discussion of Exercise 3; work on Exercise 4 (6h, in class)
Lecture 6: Asset pricing with frictions (3h, in class)
Lecture 7: Discussion of Exercise 4 (1h, hybrid)
Exercises: must be handed in before the lecture in which they are discussed. Exercise 5 should be handed in 2 weeks after the last lecture.