Empirical Asset Pricing

The popularity of the CME FedWatch as a tool for forecasting monetary policy has increased rapidly. We investigate its statistical and economic value for market participants. Our analysis shows that this simple binary model can predict the Federal Open Market Committee (FOMC) rate decisions with an 88% accuracy 30 days before FOMC meetings, compared with a 75% accuracy using conventional Fed funds futures.

Nonlinear machine learning (ML) models are increasingly used to predict the cross-section of stock returns, yet the economic justification for their nonlinear gains remains underexplored. Building on an equilibrium-based framework, this study shows that nonlinear MLs are most valuable when stock payoffs deviate from elliptical distributions (e.

Since the global financial crisis, bank complexity has faced increasing scrutiny for its impact on financial stability, yet it remains difficult to measure. We introduce a novel explainable AI method to quantify complexity and find that it exhibits a pro-cyclical pattern, rising before crises and declining during periods of distress.

While machine learning (ML) and deep learning (DL) models are increasingly applied to predict both cross-section and time series of stock returns, the underlying sources of the nonlinearities they capture remain largely unexplored.