Long time coming for us but here is Version 2.01 of our #SCOTUS Paper …
We have added three times the number years to the prediction model and now predict out-of-sample nearly two centuries of historical decisions (1816-2015). Then, we compare our results to three separate null models (including one which leverages in-sample information).
Here is the 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. Our model leverages the random forest method together with unique feature engineering to predict nearly two centuries of historical decisions (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 advance for the science of quantitative legal prediction and portend a range of other potential applications.
Enjoyed delivering the Keynote Address at the #FutureOfLaw Conference here at Aviva Stadium in Dublin, Ireland.
Thanks to Leman Solicitors and all of the sponsors for this wonderful event!
When it comes to prediction – law would benefit from better applying the tools of STEM / Finance / Insurance and so in that spirit — our company recently launched LexSemble and it allows for near frictionless crowd sourcing of predictions in law (and beyond). Many potential applications in law including early (and ongoing) case assessment in litigation, forecasting various sorts of transactional outcomes and predicting the actions of regulators, etc. It also has a range of machine learning capabilities which allow for crowd segmentation, expert weighting, natural language processing on relevant documents, etc.
Learn More: https://lexsemble.com/features.html
#FinTech embraces two major themes – characterizing / pricing increasingly exotic forms of risk and removing unnecessary frictions from friction laden financial processes. #Fin(Legal)Tech is the application of those ideas and technology to a wide range of law related spheres including litigation, transactional work and compliance.
The Law Lab at Illinois Tech – Chicago-Kent College of Law presents its first #Fin(Legal)Tech Conference on November 4, 2016. Continuing its legacy as an academic leader in legal technology and innovation, Chicago-Kent College of Law will bring together a wide-ranging and diverse group of industry leaders for a truly unique conference experience.
Attendees will be able to see rapid-fire and deeply engaging presentations on the following subjects:
Legal Risk, Legal Underwriting & Legal Insurance
Blockchain and Computable Contracts
MicroLaw / Long Tail Legal Markets
New Legal Information Infrastructure
Quantitative Legal Prediction & Legal Analytics
The Frictionless Delivery of Legal Services
Artificial Intelligence and Law
We will be soon announcing the speaker list but tickets are now open so if you want to attend please register for a FREE ticket today!
Above is my keynote address at the Janders Dean Legal Horizon Conference in Sydney. It is a mixture of some earlier talks I have given – together with some new materials.