machine learning model specifications. Each investor forms return forecasts from their own specific model using data inputs … that are available to all investors. We measure disagreement as dispersion in forecasts across investor-models. Our measure … aligns with extant measures of disagreement (e.g., analyst forecast dispersion), but is a significantly stronger predictor of …

Do individual investors have better information about local stocks? Our results demonstrate that they do. Large trading …

We examine quantity choice patterns by equity traders across trading hours in the U.S. Controlling for intraday … variations in trading activity, we find that traders submit more non-rounded order sizes and more order sizes overall leading up … differs from total trading demand, which resembles a U-shape pattern intraday, but is consistent with less trade …

In a dynamic model of financial market trading multiple heterogeneously informed traders choose when to place orders …. This behavior generates intraday patterns with decreasing spreads, decreasing probability of informed trading (PIN), and …

that there will be zero asset flow into and out of the funds, zero excess returns net of trading costs, a fixed management …

excess return forecasts. We find that perpetual learning usually delivers statistically and economically significant out …