Autoencoder Asset Pricing Models

Gu, Shihao; Kelly, Bryan T.; Xiu, Dacheng

doi:10.2139/ssrn.3335536

Cited by 58 publications

(72 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…36 Using stocks with missing characteristic information requires data imputation based on model assumptions. Gu et al (2019) replace a missing characteristic with the cross-sectional median of that characteristic during that month. However, this approach introduces an additional source of error and as it ignores the dependency structure in the characteristic space creates artificial time-series fluctuation in the characteristics, which we want to avoid.…”

Section: One Characteristic and One Macroeconomic State Processmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning in Asset Pricing

Chen¹,

2019

View full text Add to dashboard Cite

We propose a novel approach to estimate asset pricing models for individual stock returns that takes advantage of the vast amount of conditioning information, while keeping a fully flexible form and accounting for time-variation. Our general non-linear asset pricing model is estimated with deep neural networks applied to all U.S. equity data combined with a substantial set of macroeconomic and firm-specific information. We estimate the stochastic discount factor that explains all asset returns from the conditional moment constraints implied by no-arbitrage. Our asset pricing model outperforms out-of-sample all other benchmark approaches in terms of Sharpe ratio, explained variation and pricing errors. We trace its superior performance to including the no-arbitrage constraint in the estimation and to accounting for macroeconomic conditions and non-linear interactions between firm-specific characteristics. Our generative adversarial network enforces no-arbitrage by identifying the portfolio strategies with the most pricing information. Our recurrent Long-Short-Term-Memory network finds a small set of hidden economic state processes. A feedforward network captures the non-linear effects of the conditioning variables. Our model allows us to identify the key factors that drive asset prices and generate profitable investment strategies.

show abstract

Section: One Characteristic and One Macroeconomic State Processmentioning

confidence: 99%

“…Our approach also yields the conditional mean-variance efficient portfolio, but based on all stocks. Gu et al (2019) extend the linear conditional factor model of Kelly et al (2018) to a non-linear factor model using an autoencoder neural network. 5…”

Section: Introductionmentioning

confidence: 99%

Deep Learning in Asset Pricing

Chen¹,

2019

View full text Add to dashboard Cite

show abstract

“…Pelger and Xiong (2019) estimate model (21) by minimizing a local version of the Least-Squares criterion underlying PCA, where localization is implemented by kernel smoothing. In practice, the number of conditioning variables, which we can accommodate, is small.Among the nonparametric approaches, some recent work takes advantage of machine learning methods to achieve greater flexibility in the modeling of time-varying betas and accommodate the large dimensionality of the set of potential characteristics and state variables Gu et al (2019). consider the setting where the loadings are a nonparametric function of a large-dimensional vector of characteristics: b i,t = b(Z i,t−1 ), and use an autoencoder to estimate this relationship.…”

mentioning

confidence: 99%

“…consider the setting where the loadings are a nonparametric function of a large-dimensional vector of characteristics: b i,t = b(Z i,t−1 ), and use an autoencoder to estimate this relationship. Autoencoder is a class of universal approximators in the realm of Artificial Neural Networks (seeGu et al (2019) and references therein). Using L b hidden layers and an activator function g, each component of the loadings vector is approximated as:…”

mentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Large Dimensional Conditional Factor Models in Finance

2019

View full text Add to dashboard Cite

This chapter provides an econometric methodology for inference in large-dimensional conditional factor models in finance. Changes in the business cycle and asset characteristics induce time variation in factor loadings and risk premia to be accounted for. The growing trend in the use of disaggregated data for individual securities motivates our focus on methodologies for a large number of assets. The beginning of the chapter outlines the concept of approximate factor structure in the presence of conditional information, and develops an arbitrage pricing theory for large-dimensional factor models in this framework. Then we distinguish between two different cases for inference depending on whether factors are observable or not. We focus on diagnosing model specification, estimating conditional risk premia, and testing asset pricing restrictions under increasing cross-sectional and time series dimensions. At the end of the chapter, we review some of the empirical findings and contrast analysis based on individual stocks and standard sets of portfolios. We also discuss the impact on computing time-varying cost of equity for a firm, and summarize differences between results for developed and emerging markets in an international setting.

show abstract

Stock picking with machine learning

Wolff,

Echterling

2023

Journal of Forecasting

View full text Add to dashboard Cite

We analyze machine learning algorithms for stock selection. Our study builds on weekly data for the historical constituents of the S&P500 over the period from January 1999 to March 2021 and builds on typical equity factors, additional firm fundamentals, and technical indicators. A variety of machine learning models are trained on the binary classification task to predict whether a specific stock outperforms or underperforms the cross‐sectional median return over the subsequent week. We analyze weekly trading strategies that invest in stocks with the highest predicted outperformance probability. Our empirical results show substantial and significant outperformance of machine learning‐based stock selection models compared to an equally weighted benchmark. Interestingly, we find more simplistic regularized logistic regression models to perform similarly well compared to more complex machine learning models. The results are robust when applied to the STOXX Europe 600 as alternative asset universe.

show abstract

Autoencoder Asset Pricing Models

Cited by 58 publications

References 32 publications

Deep Learning in Asset Pricing

Deep Learning in Asset Pricing

Estimation of Large Dimensional Conditional Factor Models in Finance

Stock picking with machine learning

Contact Info

Product

Resources

About