Autoencoder asset pricing models

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 flexib...

Full description

Saved in:
Bibliographic Details
Published in:Journal of econometrics Vol. 222; no. 1; pp. 429 - 450
Main Authors: Gu, Shihao, Kelly, Bryan, Xiu, Dacheng
Format: Journal Article
Language:English
Published: Amsterdam Elsevier B.V 01.05.2021
Elsevier Science Publishers
Elsevier Sequoia S.A
Subjects:
Analysis
Arbitrage
Asset management
Asset pricing
assets
Autoencoder
Big data
Business schools
Conditional asset pricing model
econometrics
Economic factors
Errors
Machine learning
Neural networks
Nonlinear factor model
Nonlinear systems
Prices
Pricing
Stock returns
Nonlinear factor model
Autoencoder
Neural networks
Machine learning
Stock returns
Big data
Conditional asset pricing model
ISSN:0304-4076, 1872-6895
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0304-4076
1872-6895
DOI:10.1016/j.jeconom.2020.07.009