This paper, by two Spanish professors, aims to make predictions of Supreme Court cases based on how each justice interacts with other Justices:
Successful attempts to predict judges’ votes shed light into how legal decisions are made and, ultimately, into the behavior and evolution of the judiciary. Here, we investigate to what extent it is possible to make predictions of a justice’s vote based on the other justices’ votes in the same case. For our predictions, we use models and methods that have been developed to uncover hidden associations between actors in complex social networks. We show that these methods are more accurate at predicting justice’s votes than forecasts made by legal experts and by algorithms that take into consideration the content of the cases. We argue that, within our framework, high predictability is a quantitative proxy for stable justice (and case) blocks, which probably reflect stable a priori attitudes toward the law. We find that U.S. Supreme Court justice votes are more predictable than one would expect from an ideal court composed of perfectly independent justices. Deviations from ideal behavior are most apparent in divided 5–4 decisions, where justice blocks seem to be most stable. Moreover, we find evidence that justice predictability decreased during the 50-year period spanning from the Warren Court to the Rehnquist Court, and that aggregate court predictability has been significantly lower during Democratic presidencies. More broadly, our results show that it is possible to use methods developed for the analysis of complex social networks to quantitatively investigate historical questions related to political decision-making.
Their model was 77% accurate
The widening of the predictability gap becomes even more apparent if we limit our analysis to the cases that are, in principle, most difficult, namely those resulting in a 5–4 vote (Figs. 2E–F). Remarkably, while the majority rule only predicts 28% of these votes correctly, the stochastic block model makes the right prediction in 77% of the cases. This result may appear as a trivial consequence of a single ideological left–right divide in the Supreme Court–that is not the case. Indeed, the most common 5–justice coalition accounts for less than 50% of the 5–4 decisions of the court ; our predictions are more accurate thanks to the Bayesian approach that we use to average over all possible justice coalitions and case types.
I emailed the Profs with a link to our paper.