CMStatistics 2022: Start Registration
View Submission - CFE
Title: Conditional latent factor models via econometrics-based neural networks Authors:  Hao Ma - Queen Mary University of London (United Kingdom) [presenting]
Abstract: A hybrid methodology is developed that incorporates an econometric identification strategy into artificial neural networks when studying conditional latent factor models. The time-varying betas are assumed to be unknown functions of numerous firm characteristics, and the statistical factors are population cross-sectional OLS estimators for given beta values. Hence, identifying betas and factors boils down to identifying only the function of betas, which is equivalent to solving a constrained optimization problem. For estimation, we construct neural networks customized to solve the constrained optimization problem, which gives a feasible non-parametric estimator for the function of betas. Empirically, we conduct my analysis on a large unbalanced panel of monthly data on US individual stocks with around 30, 000 firms, 516 months, and 94 characteristics. We find that 1) the hybrid method outperforms the benchmark econometric method and the neural network's method in terms of explaining out-of-sample return variation, 2) betas are highly non-linear in firm characteristics, 3) two conditional factors explain over 95\% variation of the factor space, and 4) hybrid methods with literature-based characteristics (e.g., book-to-market ratio) outperform ones with COMPUSTAT raw features (e.g., book value and market value), emphasizing the value of academic knowledge from an angle of Man vs Machine.