We uncover momentum and reversal patterns in half-day option returns that persist for up to at least 20 business days, with economic magnitudes of 0.22% to 0.45% per half-day. Specifically, returns show strong momentum within the same period (e.g., intraday-to-intraday) but reverse sharply...

We introduce a simple yet powerful method for enhancing mutual fund performance prediction by combining individual predictors into a composite predictor. This composite approach integrates information from 19 well-established return-based and portfolio holdings-based predictors from the...

We present improved out-of-sample predictability of future fund flows using state-of-the-art machine learning methods. Nonlinear machine learning models significantly outperform linear models in terms of out-of-sample R-squared. Using interpretable ML methods, we identify past flows and the...

Theories of limited attention predict that investors rely on typical patterns to navigate high-dimensional firm characteristics, making atypical firms hard to process. To quantify this difficulty, we propose a data-driven measure of firm atypicality using an autoencoder (ATYP). The model learns...

We study the determinants of US dollar demand across market participants and traded instruments using survey-based exchange rate and macroeconomic expectations. Leveraging granular FX trading data and forward looking expectations, we present three results. First, currency investors increase...

We introduce a simple yet powerful method for enhancing mutual fund performance prediction by combining individual predictors into a composite predictor. This composite approach integrates information from 19 well-established return-based and portfolio holdings-based predictors from the...

We uncover momentum and reversal patterns in half-day option returns that persist for up to at least 20 business days, with economic magnitudes of 0.22% to 0.45% per half-day. Specifically, returns show strong momentum within the same period (e.g., intraday-to-intraday) but reverse sharply...

We present improved out-of-sample predictability of future fund flows using state-of-the-art machine learning methods. Nonlinear machine learning models significantly outperform linear models in terms of out-of-sample R-squared. Using interpretable ML methods, we identify past flows and the...

We study the determinants of US dollar demand across market participants and traded instruments using survey-based exchange rate and macroeconomic expectations. Leveraging granular FX trading data and forward looking expectations, we present three results. First, currency investors increase...

Theories of limited attention predict that investors rely on typical patterns to navigate high-dimensional firm characteristics, making atypical firms hard to process. To quantify this difficulty, we propose a data-driven measure of firm atypicality using an autoencoder (ATYP). The model learns...