We introduce a class of interpretable tree-based models (P-Tree) for analyzing (unbalanced) panel data, with iterative and global (instead of recursive and local) split criteria. We apply P-Tree to split the cross section of asset returns under the no-arbitrage condition, generating a stochastic...

We predict asset returns and measure risk premia using a prominent technique from artificial intelligence -- deep sequence modeling. Because asset returns often exhibit sequential dependence that may not be effectively captured by conventional time series models, sequence modeling offers a...

We develop a new class of tree-based models (P-Tree) for analyzing (unbalanced) panel data utilizing global (instead of local) split criteria that incorporate economic guidance to guard against overfitting while preserving interpretability. We grow a P-Tree top-down to split the cross section of...

Sparse models, though long preferred and pursued by social scientists, can be ineffective or unstable relative to large models, for example, in economic predictions (Giannone et al., 2021). To achieve sparsity for economic interpretation while exploiting big data for superior empirical...

We document that value-to-price, the ratio of Residual-Income-Model-based valuation to market price, subsumes the power of book-to-market ratio and many other value or quality measures in predicting stock returns. Long-short value-to-price portfolios hedge against momentum, revitalize the...

We model financial innovations such as Exchange-Traded Funds, smart beta products, and many index-based vehicles as composite securities that facilitate trading common factors in assets' liquidation values. Through accessing a larger basket of assets in endogenously-chosen proportions, composite...

We document characteristics-based return anomalies in a large cross-section (4,000) of crypto assets. Cryptocurrency returns exhibit momentum in the largest-cap group, reversals in other size groups, and strong crypto value and network adoption premia, from which we derive two novel factors to...