Abstract This article presents an augmented deep factor model that generates latent factors for cross-sectional asset pricing. The conventional security sorting on firm characteristics for constructing long–short factor portfolio weights is nonlinear modeling, while factors are treated as inputs in linear models. We provide a structural deep-learning framework to generalize the complete mechanism for fitting cross-sectional returns by firm characteristics through generating risk factors (hidden layers). Our model has an economic-guided objective function that minimizes aggregated realized pricing errors. Empirical results on high-dimensional characteristics demonstrate robust asset pricing performance and strong investment improvements by identifying important raw characteristic sources.

Using machine learning and many predictors, we find strong bond return predictability, with an out-of-sample R-squared of 4.48% and an annualized Sharpe ratio of 3.27. ML models identify important predictors for aggregate predictors (bond market returns, TERM and HML factors, GDP growth) and bond characteristics (downside risk, short-term reversal, return skewness, and credit spreads). Predictability varies over time, being stronger during periods of high investor risk aversion, slow economic growth, and strong cross-sectional factor explanatory power. Our results highlight the benefits of leveraging both cross-sectional and time-series predictors to forecast corporate bond returns while considering public and private bonds.

In the 1990s and the 2000s, many urban credit cooperatives in China were reformed to city commercial banks with the introduction of government ownership. We exploit this bank ownership reform as a quasi-natural experiment to evaluate its impact on corporate maturity mismatch. We find that local firms reduced reliance on short-term debt for investments by obtaining greater long-term credit. The reduction of corporate maturity mismatch is more pronounced if the city has fewer financial resources, or if the firm has greater financial constraints, R&D intensity, or market competition. Local firms’ capital allocation efficiency also increased. Our findings highlight the positive effect of government ownership in enhancing liquidity and promoting growth.

We introduce a new class of tree-based models, P-Trees, for analyzing (unbalanced) panel of individual asset returns , generalizing high-dimensional sorting with economic guidance and interpretability. Under the mean–variance efficient framework, P-Trees construct test assets that significantly advance the efficient frontier compared to commonly used test assets, with alphas unexplained by benchmark pricing models. P-Tree tangency portfolios also constitute traded factors, recovering the pricing kernel and outperforming popular observable and latent factor models for investments and cross-sectional pricing. Finally, P-Trees capture the complexity of asset returns with sparsity, achieving out-of-sample Sharpe ratios close to those attained only by over-parameterized large models.