Premium
Subsampled factor models for asset pricing: The rise of Vasa
Author(s) -
De Nard Gianluca,
Hediger Simon,
Leippold Markus
Publication year - 2022
Publication title -
journal of forecasting
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.543
H-Index - 59
eISSN - 1099-131X
pISSN - 0277-6693
DOI - 10.1002/for.2859
Subject(s) - robustness (evolution) , econometrics , computer science , portfolio , stock (firearms) , capital asset pricing model , predictive power , dimensionality reduction , artificial intelligence , mathematics , economics , financial economics , engineering , mechanical engineering , biochemistry , chemistry , philosophy , epistemology , gene
We propose a new method, variable subsample aggregation (VASA), for equity return prediction using a large‐dimensional set of factors. To demonstrate the effectiveness, robustness, and dimension reduction power of VASA, we perform a comparative analysis between state‐of‐the‐art machine learning algorithms. As a performance measure, we explore not only the global predictive but also the stock‐specificR 2's and their distribution. While the globalR 2reflects the average forecasting accuracy, we find that high variability in stock‐specificR 2's can be detrimental for the portfolio performance. Since VASA shows minimal variability, portfolios formed on this method outperform the portfolios based on random forests and neural nets.