Recent advances inNatural Language Processing andMachine Learning provide us with the tools to build predictive models that can be used to unveil patterns driving judicial decisions. This can be useful, for both lawyers and judges, as an assisting tool to rapidly identify cases and extract patterns which lead to certain decisions. This paper presents the first systematic study onpredicting the ...

People are often expected to make decisions based on all of the relevant information, weighted and combined appropriately. Under many conditions, however, people use heuristic strategies that depart from this ideal. I tested the ability of two models to predict bail decisions made by judges in two courts. In both courts, a simple heuristic proved to be a better predictor of judicial decisions t...

We model government takings of private property, embedding prominent theories of their economic consequences. Random assignment of U.S. judges and the fact that judges make takings precedent in a manner correlated with their race, political party, and prior government advocacy facilitate causal estimates of allowing government takings. Novel data on judicial biographies and takings decisions si...