Sven Lerner (ICME): Structural Deep Learning in Conditional Asset Pricing

Sven Lerner will present the paper “Structural Deep Learning in Conditional Asset Pricing”. We will provide dinners for the attendees and send out dining options on Monday. Please see more details below:

Title: Structural Deep Learning in Conditional Asset Pricing  (link here)

Authors: Jianqing Fan, Tracy Ke, Yuan Liao, Andreas Neuhierl

Abstract:
We develop new 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. Contrary to many applications of neural networks in economics, we can open the “black box” of machine learning predictions, and provide an economic interpretation of the successful predictions obtained from neural networks, by decomposing the neural predictors as risk-related and mispricing components. Our estimation method starts with period-by-period deep learning, followed by local PCAs to capture time-varying features of the model. We formally establish the asymptotic theory of the deep-learning estimators, which apply to both in-sample fit and out-of-sample predictions. We also illustrate the “doubledescent-risk” phenomena associated with over-parametrized predictions, which justifies the use of over-fitting machine learning methods.