Measuring cross-sectional variation in expected returns : a machine learning approach
Abstract/Contents
- Abstract
- I develop and test a new machine learning method for estimating cross-sectional firm-level expected returns. My approach adapts the loss function of a random forest algorithm to minimize the variance of measurement errors instead of trading off bias and variance. Out-of-sample tests show this approach yields reliably higher cross-sectional accuracy relative to: (a) commonly used implied cost of capital estimates, (b) factor-based estimates, and (c) estimates based on other state-of-the-art machine learning algorithms. In more detailed analyses, I find that while a small number of firm characteristics explain most of the returns predictability, the relative importance of these characteristics vary by holding horizon. Further, cross-sectional differences in expected returns exhibit limited persistence beyond two years. I also use this new approach to revisit the reported association between earnings smoothness and expected returns. Contrary to prior studies, I show that firms whose earnings are smoother relative to their cash flows earn higher (not lower) expected returns, despite being safer on many dimensions.
Description
| Type of resource | text |
|---|---|
| Form | electronic resource; remote; computer; online resource |
| Extent | 1 online resource. |
| Place | California |
| Place | [Stanford, California] |
| Publisher | [Stanford University] |
| Copyright date | 2023; ©2023 |
| Publication date | 2023; 2023 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Author | Laporte, Douglas Jean |
|---|---|
| Degree supervisor | Lee, Charles |
| Degree supervisor | Piotroski, Joseph D. (Joseph David) |
| Thesis advisor | Lee, Charles |
| Thesis advisor | Piotroski, Joseph D. (Joseph David) |
| Thesis advisor | McNichols, Maureen, 1953- |
| Thesis advisor | Smith, Kevin |
| Degree committee member | McNichols, Maureen, 1953- |
| Degree committee member | Smith, Kevin |
| Associated with | Stanford University, Graduate School of Business |
Subjects
| Genre | Theses |
|---|---|
| Genre | Text |
Bibliographic information
| Statement of responsibility | Douglas J. Laporte. |
|---|---|
| Note | Submitted to the Graduate School of Business. |
| Thesis | Thesis Ph.D. Stanford University 2023. |
| Location | https://purl.stanford.edu/tt780jg1481 |
Access conditions
- Copyright
- © 2023 by Douglas Jean Laporte
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...