Dr. Benjamin Moritz

Tree-based conditional portfolio sorts: The relation between past and future stock returns,
(former title: Deep conditional portfolio sorts: The relation between past and future stock returns)
with Tom Zimmermann,

2013 – Our first presentation in Harvard Research Seminar in 2013: Presentation (pdf)
2014 – Our first working paper: Paper (pdf)
2014 – An extended presentation in 2014: Presentation (pdf)
2015 – Best Paper Award at the Annual Meeting 2015 of the German Finance Association (Deutsche Gesellschaft für Finanzwirtschaft)
2016 – Cited in an article on the examination of the research process and principles underlying successful models used in quantitative equity strategies.
Cerniglia, J. A., Fabozzi, F. J., & Kolm, P. N. (2016). Best Practices in Research for Quantitative Equity Strategies. The Journal of Portfolio Management, 42(5), 135-143.
“Researchers in finance are applying these newer methodologies to create insights into the dynamics of equity markets. Moritz and Zimmermann [2014] address the research question of which variables provide independent information about the cross-section of stock returns.”
2017 – Cited in an article on applying machine learning to economics.
Mullainathan, Sendhil, and Jann Spiess. (2017). Machine Learning: An Applied Econometric Approach. Journal of Economic Perspectives, 31(2), 87-106.
“A final application of supervised machine learning is to test directly theories that are inherently about predictability. Within the efficient markets theory in finance, for example, the inability to make predictions about the future is a key prediction. Moritz and Zimmermann (2016) adapt methods from machine learning to show that past returns of US firms do have significant predictive power over their future stock prices.”
2019 – Cited in a lecture given by Stefan Nagel
Princeton Lectures in Finance 2019: Machine Learning and Asset Pricing
https://voices.uchicago.edu/stefannagel/discussions/