Growing the Efficient Frontier on Panel Trees
This addresses the problem of improving portfolio construction and asset pricing for investors and researchers, offering a more interpretable and efficient method, though it appears incremental as it builds on existing tree-based and mean-variance frameworks.
The paper tackles the problem of analyzing panel data of individual asset returns by introducing P-Trees, a new tree-based model that generalizes high-dimensional sorting with economic guidance. The result is that P-Trees significantly advance the efficient frontier compared to commonly used test assets, with out-of-sample Sharpe ratios close to those of over-parameterized large models.
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.