An Empirical Case Study of Factor Alignment Problems Using the USER Model
The practical issues that arise due to the interaction between three principal players in any quantitative strategy—namely, the alpha model, the risk model, and the constraints—are collectively referred to as factor alignment problems (FAPs). Examples of FAPs include risk-underestimation of optimized portfolios, undesirable exposure to factors with hidden and unaccounted systematic risk, consistent failure in achieving ex ante performance targets, and inability to harvest highquality alphas into an above-average information ratio (IR). This article concerns an empirical illustration of various facets of FAPs using the U.S. Expected Return (USER) model. Unlike previous studies on FAP that are either based on simulated returns or a black-box expected return model, we leverage the detailed knowledge of the USER model to create an insightful narrative. We show that optimal portfolios constructed using the USER model without taking into account the misalignment issues betray typical symptoms of FAPs and have exposure to certain hidden systematic risk factors that are not accounted for during portfolio construction. We trace the origins of these latent systematic risk factors to the constituent factors of the USER model and the turnover constraint. Finally, we leverage our understanding of the alignment issues to propose an alternative portfolio construction methodology that directly addresses FAPs. Using the proposed methodology not only gives unbiased risk forecasts, but also improves ex post performance in a statistically significant manner.