A General Approach for Predicting the Behavior of the Supreme Court of the United States

TL;DR

This paper introduces a novel machine learning model that predicts the US Supreme Court's decisions over two centuries with high accuracy, outperforming baseline models and applicable out-of-sample.

Contribution

We develop a time-evolving random forest model that predicts Supreme Court decisions across two centuries, surpassing previous models in out-of-sample accuracy.

Findings

70.2% accuracy at case outcome level

71.9% accuracy at justice vote level

Outperforms null models by nearly 5% over the past century

Abstract

Building on developments in machine learning and prior work in the science of judicial prediction, we construct a model designed to predict the behavior of the Supreme Court of the United States in a generalized, out-of-sample context. To do so, we develop a time evolving random forest classifier which leverages some unique feature engineering to predict more than 240,000 justice votes and 28,000 cases outcomes over nearly two centuries (1816-2015). Using only data available prior to decision, our model outperforms null (baseline) models at both the justice and case level under both parametric and non-parametric tests. Over nearly two centuries, we achieve 70.2% accuracy at the case outcome level and 71.9% at the justice vote level. More recently, over the past century, we outperform an in-sample optimized null model by nearly 5%. Our performance is consistent with, and improves on the general level of prediction demonstrated by prior work; however, our model is distinctive because it can be applied out-of-sample to the entire past and future of the Court, not a single term. Our results represent an important advance for the science of quantitative legal prediction and portend a range of other potential applications.