Working Paper: NBER ID: w27388
Authors: Bryan T. Kelly; Semyon Malamud; Lasse H. Pedersen
Abstract: We propose a new asset-pricing framework in which all securities’ signals are used to predict each individual return. While the literature focuses on each security’s own-signal predictability, assuming an equal strength across securities, our framework is flexible and includes cross-predictability—leading to three main results. First, we derive the optimal strategy in closed form. It consists of eigenvectors of a “prediction matrix,” which we call “principal portfolios.” Second, we decompose the problem into alpha and beta, yielding optimal strategies with, respectively, zero and positive factor exposure. Third, we provide a new test of asset pricing models. Empirically, principal portfolios deliver significant out-of-sample alphas to standard factors in several data sets.
Keywords: asset pricing; predictability; portfolio management; cross-predictability
JEL Codes: C1; C3; C5; C6; G1; G12; G14
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| prediction matrix (C53) | understanding asset returns (G12) |
| prediction matrix (C53) | principal portfolios (G19) |
| principal portfolios (G19) | expected returns (G17) |
| symmetric part of prediction matrix (C59) | strategies with positive expected returns (G11) |
| antisymmetric part of prediction matrix (C69) | strategies with zero expected returns (G40) |
| rational asset pricing models (G19) | expected returns of alpha portfolios (G11) |
| leading principal portfolios (G11) | positive returns (G12) |
| prediction matrix structure (C69) | expected returns of trading strategies (G17) |