Integrating Factor Models

Forking paths in empirical studies

“…These ideas have blossomed in the frequentist (Hansen (2007), Zhang (2015), Zhang and Liu (2019) and Zhu et al (2023)) and Bayesian (Draper (1995), Raftery et al (1997)) circles. For instance, Bayesian averaging has recently been used in Avramov et al (2023) to cope with model uncertainty.…”

Firm Fundamentals and the Cross Section of Implied Volatility Shapes

“…Our paper adds to the literature of growing applications of machine learning to finance. Rapach et al (2013), Chinco et al (2019), DeMiguel et al (2020), Feng et al (2020), Freyberger et al (2020, Gu et al (2020), Kozak et al (2020), Avramov et al (2021), Bryzgalova et al (2022Bryzgalova et al ( , 2021, Cong et al (2022), Han et al (2022), among others, focus on equities based on firm characteristics; Avramov et al (2022) and Guo et al (2022) study bonds;and Filippou et al (2022) It is important to point out that there is a lack of theoretical guidance on what exactly the firm fundamentals are that determine the IV surface. In this paper, we attempt a partial solution by using machine learning tools to identify the variables from a large set of firm fundamentals.…”

A penalized two-pass regression to predict stock returns with time-varying risk premia

“…Alternatively, Fan et al (2022) develop a nonparametric methodology for estimating conditional asset pricing models using deep neural networks, by employing time-varying conditional information on alphas and betas carried by firm-specific characteristics. Avramov et al (2022) propose a novel Bayesian approach to study time-series and cross-sectional effects in asset returns, when the true factor model and its underlying parameters are uncertain. They use macro predictors to model time-variation in the factor loadings and investigate potential mispricing.…”