Abstract
Using the universe of U.S. Circuit Court cases appealed to the Supreme Court since 1946, we show that case similarity based on Circuit Court opinions achieves better prediction accuracy of Supreme Court decisions relative to the current best prediction model, which is based on ideology of judges and trends of how they vote. Relative to the benchmark prediction accuracy of 59%, textual measures of case similarity achieve prediction accuracy of 64%. We interpret this improvement to suggest that precedent matters more than politics alone. We also offer our model available as a web application.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
