Download or read book Measuring Cross-sectional Variation in Expected Returns written by Douglas Jean Laporte and published by . This book was released on 2023 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.