How Global is Predictability? The Power of Financial Transfer Learning
62 Pages Posted: 29 Nov 2023
Date Written: November 1, 2023
We show that asset pricing has a strong global component in the sense that a common global model has stronger predictability of stock returns than local models estimated in each country - even when the global model is estimated without the use of local data. While locally estimated models add no value to a global model, asset pricing nevertheless has a small local component. To detect the local component, we develop a refined transfer learning model that gains power and precision by building off the global component, denoted the ``generalized elastic net” (GENet). We estimate that the predictive parameters are 94% global.
Keywords: Predictability, asset pricing, transfer learning, machine learning
JEL Classification: C53, C58, F3, G1, G4
Suggested Citation: Suggested Citation