Autoencoder asset pricing models

By Shihao Gu, Bryan T. Kelly, D. Xiu. Journal of Econometrics, 2020

364 citations recorded by the source corpus.

Abstract We propose a new latent factor conditional asset pricing model. Like Kelly, Pruitt, and Su (KPS, 2019), our model allows for latent factors and factor exposures that depend on covariates such as asset characteristics. But, unlike the linearity assumption of KPS, we model factor exposures as a flexible nonlinear function of covariates. Our model retrofits the workhorse unsupervised dimension reduction device from the machine learning literature – autoencoder neural networks – to incorporate information from covariates along with returns themselves. This delivers estimates of nonlinear conditional exposures and the associated latent factors. Furthermore, our machine learning framework imposes the economic restriction of no-arbitrage. Our autoencoder asset pricing model delivers out-of-sample pricing errors that are far smaller (and generally insignificant) compared to other leading factor models.

View Paper: https://www.semanticscholar.org/paper/5953bcc383c3ceb866b8ef7f7c16d166e5f2ab4d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Forest Through the Trees: Building Cross-Sections of Stock Returns (2020, unknown): “19The best performing model is a three-layer neural network, with all the tuning parameters set to the same values as in Gu, Kelly, and Xiu (2020b).”
Empirical Asset Pricing via Machine Learning (2018, background): “For machine learning approaches to this problem, see Gu et al. (2019) and Kelly et al. (2019).”