17th Online Seminar in Finance: Matthias Hanauer, Robeco & Technical University of Munich
The Institute of Finance at PUEB is pleased to announce the 17th Online Seminar in Finance.
Speaker: Matthias Hanauer, Robeco & Technical University of Munich
Title: Design Choices, Machine Learning, and the Cross-Section of Stock Returns
Abstract: We fit over one thousand machine learning models for predicting stock returns, systematically varying design choices across algorithm, target variable, feature selection, and training methodology. Our findings demonstrate that the nonstandard error in portfolio returns arising from these design choices exceeds the standard error by 59%. Furthermore, we observe a substantial variation in model performance, with monthly mean top-minus-bottom returns ranging from 0.13% to 1.98%. These findings underscore the critical impact of design choices on machine learning predictions, and we offer recommendations for model design. Finally, we identify the conditions under which non-linear models outperform linear models.
Date: March 21, 2025, 15:00 (Warsaw time)
Speaker’s bio: Dr. Matthias Hanauer is a researcher and quantitative finance expert specializing in empirical asset pricing, factor investing, and portfolio construction. He is a Director of Quantitative Research at Robeco and a postdoctoral researcher at the Technical University of Munich (TUM). His work focuses on international factor premia, ensuring robust and persistent investment strategies across markets. A CFA® charterholder, Dr. Hanauer has published in leading finance journals, such as Journal of Banking and Finance, Financial Analysts Journal, and Journal of Portfolio Management, and received awards such as the ACATIS Value Prize and CFA Germany Investment Research Award. He also co-hosts Global Factor Premia, a platform for visualizing factor returns across global markets.
Place: Teams webinar.
To register, click here: https://forms.gle/uyV8pp8tkG5MqqHE8.
Registration deadline: March 19, 2025, 15:00 (Warsaw time). The invitation to the Teams webinar will be sent on March 20, 2025.
*If the link does not work, please paste it into your browser.