Here is a (short) and interesting paper that uses an innovative approach to predict the votes of the US Supreme Court:
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.
While I have my reservations whether “trying to predict the behavior of judges, one can get insights into how legal decisions are truly made”, exercises in predicting outcomes are interesting in their own right. And this paper appears to hit the target: its predictive success rate is 83% vs. the less-than-70% success rate of existing approaches based on expert opinions and statistical models of case characteristics. Note however that each individual vote is predicted with information about how the other judges have voted on that same case which, if the votes are announced simultaneously, doesn’t provide you with any leverage in actually predicting the outcome of a case.
P.S. What is this penchant that the real scientific journals (e.g.PLoS) have for social science research based on agent-based modeling or network theory?