Autoencoder asset pricing models

DOI10.1016/J.JECONOM.2020.07.009MaRDI QIDQ2658795zbMATH OpenOpenAlexFDO

Authors Shihao Gu, Bryan Kelly, Dacheng Xiu

Publication date 24 March 2021

Published in Journal of Econometrics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.jeconom.2020.07.009

zbMATH Keywords

autoencoderbig dataconditional asset pricing modelmachine learningneural networksnonlinear factor modelstock returns

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Applications of statistics to economics (62P20) Statistical aspects of big data and data science (62R07)

Recommendations

• Short communication: Deep fundamental factor models
• Estimating latent asset-pricing factors
• Latent variable models for stochastic discount factors
• Forecasting stock returns with artificial neural networks
• Cryptoasset factor models

Cites work

• A Testing Procedure for Determining the Number of Factors in Approximate Factor Models With Large Datasets
• Arbitrage, Factor Structure, and Mean-Variance Analysis on Large Asset Markets
• Auto-association by multilayer perceptrons and singular value decomposition
• Common risk factors in the returns on stocks and bonds
• Deep learning
• Determining the Number of Factors in Approximate Factor Models
• Determining the Number of Factors in the General Dynamic Factor Model
• Efficient semiparametric estimation of the Fama-French model and extensions
• Eigenvalue ratio test for the number of factors
• Estimation of random coefficients logit demand models with interactive fixed effects
• Improved penalization for determining the number of factors in approximate factor models
• Inferential Theory for Factor Models of Large Dimensions
• Projected principal component analysis in factor models
• Reducing the Dimensionality of Data with Neural Networks
• The three-pass regression filter: a new approach to forecasting using many predictors
• Time-Varying Risk Premium in Large Cross-Sectional Equity Data Sets
• Using principal component analysis to estimate a high dimensional factor model with high-frequency data

Cited in

(24)

• Machine learning to establish proxies for investor attention: evidence of improved stock-return prediction
• Editorial for the special issue on financial econometrics in the age of the digital economy
• Neural network-based automatic factor construction
• Deep differentiable reinforcement learning and optimal trading
• Short communication: Deep fundamental factor models
• A penalized two-pass regression to predict stock returns with time-varying risk premia
• Deep-learning models for forecasting financial risk premia and their interpretations
• Machine learning architectures for price formation models
• Deep learning models for inflation forecasting
• Merging two cultures: deep and statistical learning
• Asset Pricing via the Conditional Quantile Variational Autoencoder
• Natural gradient hybrid variational inference with application to deep mixed models
• Risk factor aggregation and stress testing
• GMM estimation for high-dimensional panel data models
• Deep learning based residuals in non-linear factor models: precision matrix estimation of returns with low signal-to-noise ratio
• Asset allocation with factor-based covariance matrices
• Recurrent double-conditional factor model
• SFQRA: scaled factor-augmented quantile regression with aggregation in conditional mean forecasting
• Gaussian Process Vector Autoregressions and Macroeconomic Uncertainty
• High-dimensional conditional factor model
• Statistical Quantile Learning for Large Additive Latent Variable Models
• Significance of predictors: revisiting stock return predictions using explainable AI
• A Unified Framework for Estimation of High-Dimensional Conditional Factor Models
• Latent factor models with functional single-index loadings

Describes a project that uses

Uses Software

• darch
• Adam

This page was built for publication: Autoencoder asset pricing models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2658795)