Sunday, November 13, 2011

Supreme Court Vote Predictions via Algorithms

In John Grisham's The Appeal, mathematical/statistical algorithms were applied to forecast appellate court decisions. Albeit fiction, I had always found this concept interesting and had consulted several law school friends; who did not express as much faith in code, objective number crunching.



Well, it looks like somebody else has begun this research effort ahead of me; came across this article off Slashdot.

US Supreme Court Votes Can Be Predicted

"
...These researchers say their computational models, using methods developed to analyze complex social networks, are just as accurate in predicting a justice's decision as forecasts from legal experts.  

'We find that Supreme Court justices are significantly more predictable than one would expect from 'ideally independent' justices in 'ideal courts,' that is, free agents independently evaluating cases on their merits, free of ideology, the study said.

...In using a 'block' method, grouping justices and cases, the researchers' model correctly predicted 83 percent of votes, compared with 67.9 percent from legal experts in one study and 66.7 percent from a case-content-based algorithm.

"

It'll take time and more research publications for this concept to gain acceptance in legal industry; just as quantitative finance did with Wall St. Regardless, I genuinely believe this could offer existing legal teams a significant, objective edge against competing entities.

0 Reflections: