Working Paper: NBER ID: w31689
Authors: Antoine Didisheim; Shikun Barry Ke; Bryan T. Kelly; Semyon Malamud
Abstract: We theoretically characterize the behavior of machine learning asset pricing models. We prove that expected out-of-sample model performance—in terms of SDF Sharpe ratio and test asset pricing errors—is improving in model parameterization (or “complexity”). Our empirical findings verify the theoretically predicted “virtue of complexity” in the cross-section of stock returns. Models with an extremely large number of factors (more than the number of training observations or base assets) outperform simpler alternatives by a large margin.
Keywords: machine learning; asset pricing; model complexity; stochastic discount factor
JEL Codes: C1; C4; C58; G1; G10; G12; G14; G17
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| model complexity (C52) | out-of-sample performance (C52) |
| model complexity (C52) | pricing errors (D49) |
| model complexity (C52) | SDF Sharpe ratio (G17) |
| increasing number of factors (C39) | pricing errors (D49) |
| increasing number of factors (C39) | SDF Sharpe ratio (G17) |
| model complexity (C52) | outperforming simpler alternatives (C52) |