Empirical Asset Pricing via Machine Learning

By Shihao Gu, Bryan T. Kelly, D. Xiu. 2018

2,086 citations recorded by the source corpus.

We perform a comparative analysis of machine learning methods for the canonical problem of empirical asset pricing: measuring asset risk premiums. We demonstrate large economic gains to investors using machine learning forecasts, in some cases doubling the performance of leading regression-based strategies from the literature. We identify the best-performing methods (trees and neural networks) and trace their predictive gains to allowing nonlinear predictor interactions missed by other methods. All methods agree on the same set of dominant predictive signals, a set that includes variations on momentum, liquidity, and volatility. Authors have furnished an Internet Appendix, which is available on the Oxford University Press Web site next to the link to the final published paper online.

Subfields: Finance, Management Science and Operations Research

How researchers see this paper

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

In Finance

In Management Science and Operations Research

Citations in the corpus

Enhancing Time-Series Momentum Strategies Using Deep Neural Networks (2019, background): “Using a variety of linear, treebased and neural network models [23] demonstrate the outperformance of non-linear methods, with deep neural networks – specifically 3-layer multilayer perceptrons (MLPs) – having the best out-of-sample predictive R.”
Deep Learning for Predicting Asset Returns (2018, background): “Recent work of Kozak et al. (2017); Gu and Xiu (2018) shows the promise of machine learning based predictors in empirical ﬁnance, including traditional regularization methods and trees and.”
Machine learning in energy economics and finance: A review (2019, result): “For instance, Gu et al. (2018) evaluate several ML algorithms and conclude that they can improve the description of asset price behavior, in particular, the measurement of risk premia, in comparison to the traditional econometric methods.”
Deep Learning in Asset Pricing (2019, methodology): “Gu, Kelly, and Xiu (2019) replace a missing characteristic with the cross-sectional median of that characteristic during that month.”
Forecasting Inflation in a Data-Rich Environment: The Benefits of Machine Learning Methods (2019, positive): “The second one is based on the results of Gu, Kelly, and Xiu (2018) and is a Deep Neural Network (DeepNN) with three hidden layers and 32, 16, and 8 rectiﬁed linear units (ReLU) in each layer, respectively.”
Investor Attention and Stock Returns (2020, neutral): “Although the purpose of the current study is to show that investor attention matters for the market risk premium, it would be of interest to investigate how its predictive power could be further improved with machine learning tools (see, e.g., Gu, Kelly, and Xiu (2020) and Rapach and Zhou (2020)).”
Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models (2023, neutral): “…Manela and Moreira (2017), Hansen, McMahon, and Prat (2018), Ke, Kelly, and Xiu (2019), Ke, Montiel Olea, and Nesbit (2019), Bybee et al. (2019), Gu, Kelly, and Xiu (2020), Cohen, Malloy, and Nguyen (2020), Freyberger, Neuhierl, and Weber (2020), Lopez-Lira 2019, Binsbergen et al. (2020), Bybee…”
Bond Risk Premia with Machine Learning∗ (2018, positive): “In the context of a comprehensive evaluation of machine learning methodologies, Gu et al. (2018) provide evidence that non-linear supervised learning can substantially improve forecasts of expected stock excess returns, allowing for a better measurement of the equity risk premium.”
On LASSO for predictive regression (2018, positive): “In comparison with the extensive literature in cross-sectional environment, theoretical properties of shrinkage methods are less explored in time series models in spite of great empirical interest in macro and financial applications (Chinco et al., 2019; Giannone et al., 2018; Gu et al., 2019).”
A Survey on Machine Learning Techniques for Cyber Security in the Last Decade (2020, background): “The usage of machine learning and artiﬁcial intelligence techniques is getting expanded rapidly in different areas of life such as ﬁnance [14]–[16], education [17], medicine [18]–[21], manufacturing industry [22], and particularly in the ﬁeld of cyber security [23]–[28].”