Self-Taught Artificial Intelligence Beats Doctors at Predicting Heart Attacks (Via Science News / Plos One)

From Science News – “In the new study, Weng and his colleagues compared use of the ACC/AHA guidelines with four machine-learning algorithms: random forest, logistic regression, gradient boosting, and neural networks.”

We teach 3 out of 4 of these methods in our Legal Analytics Course (which is a machine learning for lawyers class).

The underlying paper was published in Plos One (one of my favorite journals) and the location where we recently published our US Supreme Court Prediction paper.  In that paper, we use a time evolving random forest (with the novel twist of a tree burning protocol).

Daniel Martin Katz Named Fellow Elect of the College of Law Practice Management – Ceremony at 2017 Futures Conference in Atlanta, Georgia

I am honored to be Elected as a Fellow of the College of Law Practice Management.  The College includes legal technologists, law firm leaders, corporate counsel, etc.  I am looking forward to joining many friends and colleagues who are members of the college …

A General Approach for Predicting the Behavior of the Supreme Court of the United States (PLOS One) – Final Version April 2017

Our SCOTUS Prediction Paper is now live in Plos One (one of my favorite journals) — very happy about this (thanks to Luís A. Nunes Amaral of Northwestern University for serving as our Editor).  #OpenSourceScience #SCOTUS #LegalAnalytics #LegalData #QuantitativeLegalPrediction

Exploring the Physical Properties of Regulatory Ecosystems – Professors Daniel Martin Katz + Michael J Bommarito

FutureLaw 2017 at Stanford CodeX

Yesterday was the 5th Annual Future Law Conference at Stanford CodeX.  As always, it was an exciting day to see the best in cutting edge technology (including chatbots, predictive analytics and rules based A.I.).  I moderated a morning panel entitled The Perils and Promise of Predictive Analytics in Law.  Overall – it is clear that the community is growing both domestically and abroad.